© 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. 87771
    Prev
    Next
    INDEX
    Explanations

    To do something

    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
     why
    -0.29
     otherwise
    -0.28
     what
    -0.28
    æĬĬè¿ĻäºĽ
    -0.27
    asa
    -0.26
    why
    -0.26
     react
    -0.25
    ä»Ģä¹Īåı«
    -0.25
     possible
    -0.25
    *.
    -0.25
    POSITIVE LOGITS
    åį³åı¯
    0.26
    atement
    0.25
    ieval
    0.25
    olis
    0.25
     Debbie
    0.25
    åıªæĺ¯ä¸ºäºĨ
    0.24
    flen
    0.24
    ounder
    0.24
    utsch
    0.24
    èĦ¯
    0.24
    Activations Density 0.014%

    No Known Activations