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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 71899
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     fascinated
    -0.07
     Jet
    -0.07
    .avatar
    -0.06
    饱
    -0.06
    jest
    -0.06
     conserve
    -0.06
    崚
    -0.06
    Leaf
    -0.06
     بغداد
    -0.06
     serialization
    -0.06
    POSITIVE LOGITS
    ogene
    0.07
    أوضاع
    0.07
    긷
    0.07
    nothrow
    0.07
    保證
    0.06
    独立
    0.06
     amatør
    0.06
    たら
    0.06
    보다
    0.06
    fluence
    0.06
    Activations Density 1.889%

    No Known Activations