© 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. 57715
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Fer
    -0.27
    ç³ľ
    -0.25
    çĹħæĥħ
    -0.25
     fer
    -0.24
     automát
    -0.24
     Whale
    -0.23
    ç¾Ĭ
    -0.23
    Applications
    -0.23
     automatic
    -0.23
    纵
    -0.23
    POSITIVE LOGITS
    主ä¹īæĢĿæĥ³
    0.29
    mary
    0.27
    istic
    0.26
     imperfect
    0.24
    书ä¸Ń
    0.24
    _DOC
    0.23
     Carlson
    0.23
    æĪĸèĢħåħ¶ä»ĸ
    0.23
     Shortcut
    0.23
    anism
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.