© 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. 98588
    Prev
    Next
    INDEX
    Explanations

    Why

    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
    ellaneous
    -0.30
    å®ŀæĸ½æĸ¹æ¡Ī
    -0.26
    "".
    -0.26
    åı¦æľī
    -0.26
    çİ©æ³ķ
    -0.25
    æĶĴ
    -0.25
     unge
    -0.24
     Really
    -0.24
    åħ»
    -0.24
    wards
    -0.23
    POSITIVE LOGITS
    Disposed
    0.25
    ât
    0.25
    isArray
    0.25
     BIND
    0.24
     marvel
    0.24
     gun
    0.23
     RET
    0.23
    马æĭī
    0.23
    ÊĬ
    0.23
    è´£
    0.23
    Activations Density 0.014%

    No Known Activations