© 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. 12-TRANSCODER-HP
    7. 23016
    Prev
    Next
    INDEX
    Explanations

    Averages and medians

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ
    -0.29
    (pa
    -0.28
    izers
    -0.25
    ä¸ĬéĻIJ
    -0.25
    åİĨåı²
    -0.24
     preval
    -0.24
     rede
    -0.23
    æľĢä¼ĺ
    -0.23
     hardest
    -0.23
    orne
    -0.23
    POSITIVE LOGITS
    主åĬ¨æĢ§
    0.27
    .cc
    0.26
    %%
    0.26
     likewise
    0.26
    宫
    0.26
    rat
    0.26
    ä¸ĢéĹª
    0.25
     suff
    0.25
    hee
    0.25
    çĭ¼
    0.24
    Activations Density 0.001%

    No Known Activations