© 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. 87561
    Prev
    Next
    INDEX
    Explanations

    Question words

    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
    uous
    -0.27
    ä½ĵçİ°åĩº
    -0.25
     slashes
    -0.25
     {(
    -0.24
    urai
    -0.24
     PMC
    -0.24
    æ¸ĹéĢı
    -0.24
    onta
    -0.24
    åĵį
    -0.24
    cp
    -0.23
    POSITIVE LOGITS
    eph
    0.32
    åĽ´çĿĢ
    0.29
    VP
    0.27
    åĢ¾åIJij
    0.27
     <!--
    0.26
     ihtiyacı
    0.26
    è´¥
    0.26
    çī¹æ´¾
    0.25
    vä
    0.24
    fol
    0.24
    Activations Density 0.004%

    No Known Activations