© 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. 75335
    Prev
    Next
    INDEX
    Explanations

    disease

    np_max-act · gemini-2.0-flash
    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
     Ø
    -0.07
    ện
    -0.07
    既是
    -0.07
    几分钟
    -0.07
    ør
    -0.07
    铣
    -0.07
    ören
    -0.07
    もらえ
    -0.06
    无数次
    -0.06
    anness
    -0.06
    POSITIVE LOGITS
    _tags
    0.07
    _SUPER
    0.07
     TAG
    0.07
     warped
    0.07
     rallied
    0.06
     mob
    0.06
    	Path
    0.06
     mayoría
    0.06
    	post
    0.06
     SNAP
    0.06
    Activations Density 0.006%

    No Known Activations