© 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. 31-TRANSCODER-HP
    7. 17966
    Prev
    Next
    INDEX
    Explanations

    article/code text passages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    好人
    -0.27
    út
    -0.26
    testCase
    -0.26
    èĥľè´Ł
    -0.25
    åĮĻ
    -0.25
    åĮłå¿ĥ
    -0.25
     chip
    -0.25
    ä½ľå¼Ĭ
    -0.25
    tek
    -0.24
    çĶŁæĹ¥
    -0.24
    POSITIVE LOGITS
    -ren
    0.27
    иÑĢов
    0.26
    catch
    0.26
    个å°ı
    0.26
    Asked
    0.26
     lease
    0.26
    åĨľæĿij
    0.25
    	Transform
    0.25
    å¸ĤåľºåĮĸ
    0.25
    efined
    0.25
    Activations Density 0.008%

    No Known Activations