© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26141
    Prev
    Next
    INDEX
    Explanations

    drug use

    np_max-act · gemini-2.0-flash

    references to illegal hard drugs—especially stimulant use/production and related slang, users, and trafficking contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misleading
    -0.07
    מטפל
    -0.06
     file
    -0.06
    確
    -0.06
    Ä
    -0.06
    unità
    -0.06
    breaking
    -0.06
    启
    -0.06
    ❣
    -0.06
     spooky
    -0.06
    POSITIVE LOGITS
     undertake
    0.07
    نسي
    0.07
    _tags
    0.07
     legion
    0.07
     empez
    0.07
     Refugee
    0.07
    _rectangle
    0.07
    alert
    0.07
     большое
    0.07
    怔
    0.07
    Activations Density 0.043%

    No Known Activations