© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 70188
    Prev
    Next
    INDEX
    Explanations

    on

    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
     [("
    -0.07
     severed
    -0.07
     lastname
    -0.07
    봄
    -0.07
    一阵
    -0.07
    늣
    -0.07
    뚠
    -0.07
    przedsiębiorstw
    -0.06
    欢快
    -0.06
    prenom
    -0.06
    POSITIVE LOGITS
    sole
    0.07
     khẳng
    0.07
    그래
    0.07
     mundial
    0.07
    סים
    0.07
    ias
    0.06
     Cabinets
    0.06
    FIG
    0.06
    รห
    0.06
    GINE
    0.06
    Activations Density 0.035%

    No Known Activations