© 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. 97975
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
    s
    -0.28
    iz
    -0.27
    it
    -0.27
    è¹´
    -0.26
    mean
    -0.26
     like
    -0.26
    ance
    -0.26
     experiment
    -0.26
     nghá»ģ
    -0.26
    H
    -0.25
    POSITIVE LOGITS
    jom
    0.27
    åIJĮäºĭ们
    0.26
    >>↵↵
    0.25
    éļIJéļIJ
    0.25
     msm
    0.25
     winters
    0.24
    **č↵
    0.24
    $header
    0.24
    _č↵č↵
    0.23
    ...]↵↵
    0.23
    Activations Density 0.015%

    No Known Activations