© 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. 35-TRANSCODER-HP
    7. 40498
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equipments
    -0.28
    a
    -0.27
    ä»Ģä¹ĪæĦıæĢĿ
    -0.25
    -hidden
    -0.25
     dosage
    -0.24
    terror
    -0.24
    -split
    -0.23
    áĢĵ
    -0.23
     stead
    -0.23
    sweet
    -0.23
    POSITIVE LOGITS
    ador
    0.28
    anning
    0.28
    ubbo
    0.26
    idding
    0.26
     LLC
    0.26
    ad
    0.26
    ycz
    0.26
     Fellow
    0.26
    AD
    0.26
    ogg
    0.26
    Activations Density 0.791%

    No Known Activations