© 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. 130139
    Prev
    Next
    INDEX
    Explanations

    substance effects on biological process

    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
    åĽłä¸ºä»ĸ
    -0.29
    缯
    -0.27
    åĽłä¸ºä»ĸ们
    -0.26
    ä¹ĭæīĢ以
    -0.26
    andler
    -0.26
     Carr
    -0.26
    (undefined
    -0.25
    tsky
    -0.24
    è¡Ĺä¸Ĭ
    -0.24
    åĽłä¸ºå¥¹
    -0.23
    POSITIVE LOGITS
    antium
    0.27
    æ±ĩ
    0.26
     suç
    0.25
    èĺijèıĩ
    0.23
    éĻĦ
    0.23
     planetary
    0.23
    utes
    0.23
    onica
    0.22
    é¾Ļæ³ī
    0.22
    onia
    0.22
    Activations Density 0.024%

    No Known Activations