© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    6. 70029
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    致命
    -0.08
    下单
    -0.07
    +len
    -0.07
    뵨
    -0.07
     touchscreen
    -0.07
    木质
    -0.07
    我院
    -0.07
     이번
    -0.07
     TString
    -0.07
     adolescente
    -0.07
    POSITIVE LOGITS
    .W
    0.07
    creasing
    0.07
    .general
    0.07
    .D
    0.07
    は
    0.07
    生产和
    0.07
     estimating
    0.06
    cop
    0.06
     ','.
    0.06
    .St
    0.06
    Activations Density 0.060%

    No Known Activations