© 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. 38740
    Prev
    Next
    INDEX
    Explanations

    Code/random snippets

    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
     sát
    -0.27
    Insets
    -0.25
     absor
    -0.25
    çĨ¬
    -0.25
    éĽĨä½ĵ
    -0.25
     arrange
    -0.25
    éĩįåŀĭ
    -0.24
    erville
    -0.23
    Abs
    -0.23
    PageRoute
    -0.23
    POSITIVE LOGITS
    ug
    0.41
    ugged
    0.32
    ugi
    0.31
    usk
    0.30
     ug
    0.29
    UG
    0.28
    ugs
    0.28
    ugging
    0.28
    icho
    0.27
    used
    0.27
    Activations Density 2.399%

    No Known Activations