© 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. 15-RESID-POST-AA
    6. 1353
    Prev
    Next
    INDEX
    Explanations

    varied snippets of text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝑎
    -0.07
     Bài
    -0.07
    턱
    -0.07
    _SAMPLE
    -0.07
    哱
    -0.07
    共鸣
    -0.07
    <Key
    -0.06
    _UDP
    -0.06
    集体经济
    -0.06
    (holder
    -0.06
    POSITIVE LOGITS
     poorest
    0.08
     intended
    0.07
     financial
    0.07
     piping
    0.07
     cert
    0.07
     ساعات
    0.07
    );\
    0.07
    _ts
    0.07
     broken
    0.07
     instructions
    0.07
    Activations Density 0.000%

    No Known Activations