© 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. 97731
    Prev
    Next
    INDEX
    Explanations

    Ball

    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
    /owl
    -0.27
    沿éĢĶ
    -0.25
    undy
    -0.25
    еÑģп
    -0.25
    swers
    -0.24
     Align
    -0.24
    -</
    -0.23
     harmon
    -0.23
    /io
    -0.23
    rens
    -0.23
    POSITIVE LOGITS
    åħ³åı£
    0.24
    åħ³
    0.24
    =@"
    0.23
    ,readonly
    0.23
    ç»ĦæĪIJçļĦ
    0.23
     "`
    0.23
     specifics
    0.23
    an
    0.23
    ımı
    0.23
    @implementation
    0.22
    Activations Density 0.000%

    No Known Activations