Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 115207
    Prev
    Next
    INDEX
    Explanations

    ur

    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
     spoil
    -0.07
    _ELEM
    -0.07
     Inspection
    -0.07
     ночь
    -0.06
    ないと
    -0.06
    ウォー
    -0.06
     txn
    -0.06
    这样一来
    -0.06
     bomb
    -0.06
    صن
    -0.06
    POSITIVE LOGITS
     Fore
    0.07
    חפש
    0.07
    Fore
    0.06
    用力
    0.06
    vars
    0.06
    Routes
    0.06
    לוח
    0.06
    Living
    0.06
    关税
    0.06
    Chief
    0.06
    Activations Density 0.001%

    No Known Activations