© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9921
    Prev
    Next
    INDEX
    Explanations

    to/for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¿ħ
    -0.28
    ç¼ļ
    -0.26
     Bundle
    -0.25
    iti
    -0.24
    è¿Ļä½į
    -0.24
     SOS
    -0.24
    å®ŀæŶ
    -0.24
     bols
    -0.23
    åĪ¶åĬ¨
    -0.23
    ings
    -0.23
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.28
    %i
    0.28
    enance
    0.27
    è´¡çĮ®
    0.27
     cyn
    0.26
    为äºĨ让
    0.26
    çݯå¢ĥ
    0.26
    ayload
    0.26
    å®ĺæĸ¹
    0.25
    \core
    0.25
    Activations Density 0.004%

    No Known Activations