© 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. 129534
    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
    æħĭ
    -0.30
     ali
    -0.26
    æĪ¡
    -0.25
    èģĶ社
    -0.25
    æĺ¯åIJ¦åŃĺåľ¨
    -0.25
     addresses
    -0.25
    åħ¥å¸Ĥ
    -0.25
    ä»ħä¾Ľ
    -0.25
    ãģ¶ãĤĬ
    -0.24
    ç¾İ人
    -0.24
    POSITIVE LOGITS
    latable
    0.27
    该
    0.25
    preter
    0.24
    æŃ¥æŃ¥
    0.24
    åıªè§ģ
    0.24
    寸
    0.24
     anale
    0.24
    plaint
    0.24
    ä¸ĢçĤ¹
    0.24
    emotion
    0.24
    Activations Density 3.740%

    No Known Activations

    This feature has no known activations.