© 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. 24277
    Prev
    Next
    INDEX
    Explanations

    negation or inability

    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
    里
    -0.07
    ,"
    -0.07
     cá
    -0.07
     running
    -0.07
    lässig
    -0.07
     filed
    -0.07
     будут
    -0.06
    كرة
    -0.06
    ’S
    -0.06
     Romans
    -0.06
    POSITIVE LOGITS
    䁖
    0.07
     Blade
    0.07
    رصد
    0.07
    ⚚
    0.07
    修建
    0.07
    服饰
    0.07
     Diablo
    0.06
    maid
    0.06
    筹建
    0.06
     attendant
    0.06
    Activations Density 0.067%

    No Known Activations