© 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. 130174
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ä¸Ģ件äºĭæĥħ
    -0.28
    éĩįå¤§é¡¹çĽ®
    -0.27
    åIJĦ个æĸ¹éĿ¢
    -0.27
     greatest
    -0.27
    æİĴéĺŁ
    -0.26
    å¾Īå¤ļäºĭæĥħ
    -0.25
    åĮĸè¿Ľç¨ĭ
    -0.25
    çĭĢæ³ģ
    -0.25
    lates
    -0.25
     relationships
    -0.25
    POSITIVE LOGITS
    igu
    0.26
    ">#
    0.25
    .edu
    0.25
    åĪ»
    0.25
    ër
    0.24
    ç»Ħ
    0.24
     Mär
    0.24
    ë²Ī
    0.24
    opot
    0.24
    esan
    0.23
    Activations Density 0.017%

    No Known Activations