© 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. 53251
    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
     Arabia
    -0.29
    ç®ĹäºĨ
    -0.27
    orque
    -0.26
    quisition
    -0.25
    éĢģç»Ļ
    -0.24
    aktu
    -0.24
    _Application
    -0.24
    æ´ŀå¯Ł
    -0.24
     Ä°l
    -0.24
    roker
    -0.24
    POSITIVE LOGITS
     alike
    0.31
    ay
    0.28
     spender
    0.25
     nao
    0.25
     اÙĦبÙĦ
    0.25
    è®°å¿Ĩ
    0.25
    æŁĶ软
    0.25
     blanc
    0.24
    å¿ĥçģµ
    0.23
    ksi
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.