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. 19-RESID-POST-AA
    6. 75816
    Prev
    Next
    INDEX
    Explanations

    .annotations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _MUL
    -0.08
     lle
    -0.07
    ().'
    -0.07
    볽
    -0.07
    …I
    -0.07
    בסיס
    -0.07
    ())[
    -0.07
     Capcom
    -0.07
    *I
    -0.07
    🤧
    -0.06
    POSITIVE LOGITS
     kwargs
    0.08
    OutOf
    0.08
     offering
    0.07
     ferment
    0.07
    做饭
    0.07
    معايير
    0.07
     estimates
    0.07
    ,g
    0.07
    和尚
    0.07
    꿘
    0.07
    Activations Density 0.001%

    No Known Activations