© 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. 40752
    Prev
    Next
    INDEX
    Explanations

    say ".h" endings

    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
    Negative Logits
    os
    -0.33
     mark
    -0.33
    emark
    -0.33
    æłĩè®°
    -0.32
     marking
    -0.31
    Mark
    -0.30
    mark
    -0.28
     Mark
    -0.28
     marks
    -0.28
     Marks
    -0.27
    POSITIVE LOGITS
    ä¹İ
    0.32
    plevel
    0.28
    prise
    0.27
    ģı
    0.27
    dependent
    0.27
    missions
    0.27
    relations
    0.25
    .listen
    0.25
    patible
    0.25
    ÄŁer
    0.24
    Activations Density 3.578%

    No Known Activations