© 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. 33-TRANSCODER-HP
    7. 53828
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åijĬè¯ī大家
    -0.29
    gree
    -0.29
    #ad
    -0.27
    ä¸Ĭæ¦ľ
    -0.26
    ucht
    -0.25
    å®īåħ¨ç®¡çIJĨ
    -0.25
    æľŁåĨħ
    -0.25
    alin
    -0.25
    æŶéĹ´åĨħ
    -0.25
    ä»Ĭ天çļĦ
    -0.24
    POSITIVE LOGITS
    çļĦåľ°æĸ¹
    0.31
    éļıæīĭ
    0.27
    morph
    0.27
    ä¸ĢéĹ´
    0.26
     Schultz
    0.26
     kernels
    0.26
    deploy
    0.25
    ÑĦон
    0.25
    åı©
    0.25
    _operator
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.