© 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. 23-TRANSCODER-HP
    7. 25444
    Prev
    Next
    INDEX
    Explanations

    descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¹Łæľī
    -0.26
    ãģıãĤĮ
    -0.25
     slugg
    -0.23
    @section
    -0.23
     premises
    -0.22
    iges
    -0.22
    olas
    -0.22
    dated
    -0.22
     Sidd
    -0.22
    /documents
    -0.22
    POSITIVE LOGITS
    çĦ¶åIJİ
    1.06
     then
    0.96
    çĦ¶åIJİåĨį
    0.94
    æİ¥çĿĢ
    0.89
    çĦ¶å¾Į
    0.86
     Then
    0.84
    Then
    0.82
    then
    0.82
     заÑĤем
    0.81
    éļıåIJİ
    0.80
    Activations Density 0.003%

    No Known Activations