© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39755
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    :".$
    -0.27
    ãĢįãĢĮ
    -0.26
    A
    -0.26
    isi
    -0.26
    AC
    -0.26
    ma
    -0.26
     Classroom
    -0.26
    mans
    -0.25
    ']=='
    -0.25
    RS
    -0.25
    POSITIVE LOGITS
     oz
    0.33
     ozone
    0.31
     ounces
    0.31
    nze
    0.31
     Ezra
    0.28
    ätz
    0.28
     Zelda
    0.28
     Gaza
    0.28
     filthy
    0.28
    viz
    0.28
    Activations Density 22.593%

    No Known Activations