© 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. 33-TRANSCODER-HP
    7. 52724
    Prev
    Next
    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mand
    -0.27
    -bin
    -0.26
    çŀ³
    -0.26
     Afr
    -0.25
     incorrectly
    -0.25
    atas
    -0.25
    ioxid
    -0.24
    .Compile
    -0.24
     Mand
    -0.24
    æ·±è¿ľ
    -0.23
    POSITIVE LOGITS
    主ä¹īæĢĿæĥ³
    0.38
    è£Ĥ
    0.28
    z
    0.27
    EAR
    0.27
    æľŁ
    0.27
    asers
    0.26
    zá
    0.26
    za
    0.26
    gence
    0.25
    èIJ¥
    0.25
    Activations Density 0.062%

    No Known Activations