© 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. 107634
    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
    ãĥ¼ãĥĹ
    -0.30
    aris
    -0.28
    кÑģ
    -0.26
     Through
    -0.25
    PTY
    -0.25
    itage
    -0.24
    arra
    -0.24
    ãĤ¿ãĥ«
    -0.24
    éĢļè¿ĩ
    -0.24
    oods
    -0.24
    POSITIVE LOGITS
     citation
    0.28
    $body
    0.27
    éĺ¶æ¢¯
    0.26
    ä¸īå±Ĥ
    0.26
    äºĨä¸Ģ份
    0.25
    olith
    0.24
    çľĭäºĨä¸Ģ
    0.24
    osit
    0.24
    èĥİ
    0.24
    .glide
    0.23
    Activations Density 41.910%

    No Known Activations

    This feature has no known activations.