© 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. 108179
    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
    quier
    -0.28
    å·¦åı³
    -0.28
    计ç®ĹåĻ¨
    -0.26
     IDM
    -0.25
    ?key
    -0.25
    æ¸ħæĺİ
    -0.24
    inges
    -0.24
    _Dep
    -0.24
    ocratic
    -0.24
    quirer
    -0.23
    POSITIVE LOGITS
    unks
    0.26
    æ¿ī
    0.25
     sail
    0.23
    di
    0.23
    akt
    0.23
    ãģļ
    0.23
     diag
    0.23
    ãģĮå§ĭ
    0.22
     Authorities
    0.22
    ä¹Łæĺ¯ä¸Ģ个
    0.22
    Activations Density 14.124%

    No Known Activations

    This feature has no known activations.