© 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. 130152
    Prev
    Next
    INDEX
    Explanations

    in

    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
    åĩ¡æľ¬ç½ij
    -0.29
    æĥ³èµ·
    -0.28
    ниÑĨ
    -0.28
    pered
    -0.26
    æĥ³èµ·æĿ¥
    -0.25
    aniu
    -0.25
    å¨ĺ家
    -0.25
     compensate
    -0.24
    çľĭæ¸ħ
    -0.23
    家éĩĮ
    -0.23
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.28
    catch
    0.26
    åĨ³å¿ĥ
    0.26
    许
    0.25
    ä»Ģ
    0.24
    endez
    0.24
     rare
    0.24
    éĸĵéģķãģĦ
    0.24
    bsp
    0.24
    contr
    0.24
    Activations Density 3.985%

    No Known Activations