© 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. 12-TRANSCODER-HP
    7. 22296
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    é¢ĦæľŁ
    -0.27
    yor
    -0.26
    å¾ĹäºĨ
    -0.25
    lixir
    -0.24
    thur
    -0.24
    人éĹ´
    -0.23
    ä¼ļ
    -0.23
    æĢģ
    -0.23
    æİĴæĶ¾
    -0.23
    shaw
    -0.23
    POSITIVE LOGITS
    ahoma
    0.33
    éĴIJ
    0.31
     originals
    0.30
    SSIP
    0.26
    åĽĽäºĶ
    0.26
     оÑĢигинал
    0.26
     Lindsay
    0.25
    OSC
    0.25
    æģ»
    0.25
    abel
    0.24
    Activations Density 0.000%

    No Known Activations