© 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. 27-TRANSCODER-HP
    7. 9388
    Prev
    Next
    INDEX
    Explanations

    Due

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éī´äºİ
    -0.33
    æĹ¢çĦ¶
    -0.29
    umps
    -0.27
    çĶ±æĸ¼
    -0.27
    ctal
    -0.27
    asio
    -0.26
    umped
    -0.26
    çĶ±äºİ
    -0.25
     stabil
    -0.24
    ump
    -0.24
    POSITIVE LOGITS
    åİŁåĽł
    0.31
    çŃĶåºĶ
    0.29
    溯æºIJ
    0.28
     Reasons
    0.27
    orig
    0.26
    ollapse
    0.26
    çĶŁçī©åѦ
    0.26
    ç§įç§į
    0.26
    Clock
    0.25
    efeller
    0.25
    Activations Density 0.823%

    No Known Activations