© 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. 20-TRANSCODER-HP
    7. 107764
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOT
    -0.26
    odore
    -0.25
     AIM
    -0.25
    _WM
    -0.24
    herited
    -0.24
    kinson
    -0.24
     KeyEvent
    -0.24
     useful
    -0.24
    å·¥ä½ľæľºåĪ¶
    -0.23
    ä¿¡æģ¯å®īåħ¨
    -0.23
    POSITIVE LOGITS
     dy
    0.28
    è´µæĹı
    0.28
    unes
    0.28
     gym
    0.27
     bil
    0.25
    åĨĻä½ľ
    0.25
    éħįæĸĻ
    0.24
     trace
    0.24
     harm
    0.24
    _FRONT
    0.24
    Activations Density 28.837%

    No Known Activations

    This feature has no known activations.