© 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. 27-TRANSCODER-HP
    7. 8049
    Prev
    Next
    INDEX
    Explanations

    force

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĵãģ¨
    -0.32
    tons
    -0.29
    tone
    -0.28
    ting
    -0.27
    respond
    -0.25
    dest
    -0.25
    technical
    -0.24
    å¸Ī
    -0.24
    ized
    -0.23
    ing
    -0.23
    POSITIVE LOGITS
    fully
    0.35
    fulness
    0.32
    bite
    0.30
    ç®Ń
    0.28
     Perspective
    0.25
    fef
    0.25
    å¾IJ
    0.25
    feld
    0.25
    ful
    0.25
    idon
    0.25
    Activations Density 0.021%

    No Known Activations