© 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. 40483
    Prev
    Next
    INDEX
    Explanations

    code/math expressions

    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
    以åıĬåħ¶ä»ĸ
    -0.27
     begun
    -0.26
    å±ķå¼Ģ
    -0.26
     {}\
    -0.25
    UTO
    -0.25
     dangerously
    -0.24
    å¼Ģå±ķ
    -0.24
    èģ¿
    -0.23
     influencing
    -0.23
     measurable
    -0.23
    POSITIVE LOGITS
    为空
    0.26
    ral
    0.25
     default
    0.25
    Replacement
    0.25
    请大家
    0.25
    baugh
    0.24
    production
    0.24
    iscard
    0.24
     balk
    0.24
    enden
    0.24
    Activations Density 61.238%

    No Known Activations