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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87813
    Prev
    Next
    INDEX
    Explanations

    hy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.30
    ners
    -0.29
    standing
    -0.29
    naire
    -0.29
    hood
    -0.28
    nya
    -0.28
    case
    -0.28
    ment
    -0.28
    ship
    -0.27
    owski
    -0.27
    POSITIVE LOGITS
     thôi
    0.26
    isure
    0.26
    clus
    0.25
    å¾ģæ±Ĥ
    0.25
    æħĭ度
    0.24
    ῦ
    0.24
    rganization
    0.23
    _population
    0.23
    çĬ¶åĨµ
    0.23
    ej
    0.23
    Activations Density 0.368%

    No Known Activations