© 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. 39642
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _BOOT
    -0.28
    çĶ¨å¾®ä¿¡
    -0.27
    课åłĤæķĻåѦ
    -0.26
    ç¿»å¼Ģ
    -0.26
     opener
    -0.26
     wherever
    -0.25
    奢
    -0.25
     Hen
    -0.25
     Cru
    -0.24
    rh
    -0.24
    POSITIVE LOGITS
    paired
    0.29
    æĸ½
    0.28
    acted
    0.26
    arms
    0.25
    rouch
    0.25
    ::__
    0.25
    conde
    0.24
    åħ¨ç¨ĭ
    0.24
    鼶
    0.24
    zilla
    0.24
    Activations Density 0.038%

    No Known Activations

    This feature has no known activations.