© 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. 98115
    Prev
    Next
    INDEX
    Explanations

    reason

    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
    acf
    -0.27
     nors
    -0.26
    åĬ¨
    -0.25
     acknow
    -0.24
    recio
    -0.24
     hers
    -0.24
     titular
    -0.23
    swer
    -0.23
    IENT
    -0.23
     Cock
    -0.23
    POSITIVE LOGITS
    åŁŁ
    0.28
    åįģä¸īæĿ¡
    0.27
    LOS
    0.24
    velt
    0.24
     stamp
    0.24
    åı¦ä¸Ģä½į
    0.24
    åįĥ
    0.24
     mixed
    0.23
    å°ıä¼ĻåŃIJ
    0.23
     frame
    0.23
    Activations Density 0.078%

    No Known Activations