© 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. 53666
    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
    éĻ¡
    -0.26
    /MIT
    -0.25
    ckt
    -0.25
    蹬
    -0.25
    orny
    -0.25
    à¸ģาย
    -0.25
    å¾Ĵ
    -0.25
     Mk
    -0.24
    ¹Ħ
    -0.24
    èĤĥ
    -0.24
    POSITIVE LOGITS
    пиÑģание
    0.24
    \Client
    0.24
    ifndef
    0.23
    æĭīæĸ¯
    0.23
     EVER
    0.23
    ä¹Łåı¯
    0.23
    (Web
    0.23
     spray
    0.23
    é£İæĻ¯
    0.22
    ration
    0.22
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.