© 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. 88001
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ouston
    -0.34
     moreover
    -0.28
    ält
    -0.27
    érica
    -0.26
    oola
    -0.25
    åĪĨ彩
    -0.25
     zwar
    -0.25
    volution
    -0.25
    yleft
    -0.24
     bubb
    -0.24
    POSITIVE LOGITS
    Various
    0.29
     Total
    0.27
     T
    0.26
    TOT
    0.25
    urs
    0.25
    Total
    0.25
    带ä¸Ĭ
    0.25
    иÑĤеÑĤ
    0.24
    инд
    0.24
     ÑĦон
    0.24
    Activations Density 0.131%

    No Known Activations