© 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. 141929
    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
     balk
    -0.28
    UED
    -0.26
    èģĶåIJĪ
    -0.26
    spr
    -0.26
    '):č↵
    -0.26
    åħĥ
    -0.25
    éĴŁ
    -0.25
    THON
    -0.24
    æ²
    -0.24
    anter
    -0.24
    POSITIVE LOGITS
    otos
    0.28
    èı©æıIJ
    0.26
     Included
    0.26
    ocumented
    0.25
    former
    0.24
    ä¸ªå·¥ä½ľæĹ¥
    0.24
     correctly
    0.24
    被æįķ
    0.24
     incl
    0.24
    å½ĵäºĭ人
    0.24
    Activations Density 50.128%

    No Known Activations

    This feature has no known activations.