© 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. 63196
    Prev
    Next
    INDEX
    Explanations

    Alice in Wonderland

    np_max-act · gemini-2.0-flash
    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
     accurate
    -0.28
    zÄħd
    -0.27
    å·´æĭī
    -0.25
    ä¸įå¿į
    -0.25
    ActionTypes
    -0.25
    æľµ
    -0.25
    izen
    -0.25
    à¸Ĺำà¸ģาร
    -0.25
    é½IJ
    -0.25
    ritable
    -0.24
    POSITIVE LOGITS
    æģ
    0.27
    nce
    0.27
    acements
    0.24
    åıijä½ľ
    0.24
    éŃĩ
    0.24
     Spr
    0.23
     dunk
    0.23
    uent
    0.23
    è¾ĥå¿«
    0.23
     TS
    0.23
    Activations Density 2.767%

    No Known Activations