© 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. 35-TRANSCODER-HP
    7. 40234
    Prev
    Next
    INDEX
    Explanations

    Code and miscellaneous snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭī
    -0.27
    æ´»åĬ¨ä¸Ń
    -0.26
     habil
    -0.26
    æ´»åĬ¨
    -0.24
     leaderboard
    -0.24
    æį¢æĿ¥
    -0.24
    batch
    -0.23
    ä¸ĩ象
    -0.23
    bject
    -0.23
     depend
    -0.23
    POSITIVE LOGITS
    rant
    0.29
    å¾Ĺ以
    0.25
    夫妻
    0.25
    /MIT
    0.24
    OUNDS
    0.24
    onto
    0.24
    ountain
    0.24
    夫å¦ĩ
    0.24
    oward
    0.23
    /copyleft
    0.23
    Activations Density 0.696%

    No Known Activations