© 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. 32-TRANSCODER-HP
    7. 40927
    Prev
    Next
    INDEX
    Explanations

    take or me

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¶ħ
    -0.30
    é«ĺäºİ
    -0.28
    ä½İä½į
    -0.28
     dazz
    -0.27
    ixin
    -0.26
    çºł
    -0.26
    rex
    -0.26
    ceed
    -0.26
    å¯ĴåĨ·
    -0.26
    æ¾Ħ
    -0.25
    POSITIVE LOGITS
     most
    0.57
     place
    0.53
     places
    0.45
     Most
    0.44
    most
    0.43
    Most
    0.40
    -most
    0.40
    ä¸ŃæľĢ
    0.36
     under
    0.36
     well
    0.36
    Activations Density 0.006%

    No Known Activations