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. 85072
    Prev
    Next
    INDEX
    Explanations

    financial crisis

    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
    boy
    -0.07
    镇
    -0.06
     vak
    -0.06
    予
    -0.06
    곬
    -0.06
    OK
    -0.06
     Tiên
    -0.06
    -show
    -0.06
     beer
    -0.06
    .rank
    -0.06
    POSITIVE LOGITS
    حامل
    0.07
    (([
    0.07
    回想
    0.07
     backdrop
    0.07
     wh
    0.07
    绖
    0.07
     Compound
    0.07
    瘅
    0.07
     Thursday
    0.07
     URL
    0.07
    Activations Density 0.037%

    No Known Activations