© 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. 112243
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĺİæĻº
    -0.24
     separate
    -0.24
    磶
    -0.24
    >Select
    -0.24
    èĿĹ
    -0.23
    omanip
    -0.23
    åįļ
    -0.23
    .getLogger
    -0.23
    _lens
    -0.23
    åĪ©æ¶¦çİĩ
    -0.23
    POSITIVE LOGITS
    åŃĺåľ¨çĿĢ
    0.30
     Alo
    0.26
    åŃĶ
    0.26
    stakes
    0.25
    leh
    0.25
    uality
    0.25
    hv
    0.25
    è·ĸ
    0.25
    Mario
    0.25
    AAAAAAAA
    0.25
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.