© 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. 53677
    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
     Holding
    -0.29
    =@"
    -0.28
     holding
    -0.28
    ä½łè¿ĺ
    -0.26
     Yankee
    -0.26
    acked
    -0.26
    ophil
    -0.25
     HOLD
    -0.25
    éŀ
    -0.25
    fts
    -0.25
    POSITIVE LOGITS
    changer
    0.28
    chan
    0.27
    å°ıçĶ·åŃ©
    0.27
     depths
    0.26
    .flush
    0.25
    ä¸īè§Ĵ
    0.25
    ä¸ŃåĮ»èį¯
    0.25
    еÑĤÑģÑı
    0.25
    å¡Ķ
    0.24
    å¹´ä¹ĭä¹ħ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.