© 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. 53039
    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
    常åĬ¡åī¯
    -0.26
    valor
    -0.25
     Cot
    -0.25
     veces
    -0.24
     cot
    -0.24
    ç®ķ
    -0.23
    zens
    -0.23
     getClient
    -0.23
    èĻ¢
    -0.23
    robot
    -0.23
    POSITIVE LOGITS
    mát
    0.31
    åĴ
    0.29
     Practices
    0.27
    alink
    0.26
    éĵĻ
    0.26
     hmm
    0.25
    æµ·è¿IJ
    0.25
    çIJ¥
    0.25
    å½¢
    0.25
     qualifying
    0.25
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.