© 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. 27-TRANSCODER-HP
    7. 8224
    Prev
    Next
    INDEX
    Explanations

    of

    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
    æľī幸
    -0.29
    çľĭä»ĸ
    -0.27
    éĤ£äºĽ
    -0.27
    LEC
    -0.26
     Prem
    -0.26
     legally
    -0.26
    羣å®ŀçļĦ
    -0.26
    çľĭä½ł
    -0.25
    (fig
    -0.25
    azzi
    -0.25
    POSITIVE LOGITS
    -BEGIN
    0.24
    defaultValue
    0.24
    èķī
    0.24
    ÃŃt
    0.24
    sworth
    0.24
    çŃīæĸ¹éĿ¢çļĦ
    0.24
    charts
    0.23
    桦
    0.23
    arrays
    0.23
    anuts
    0.23
    Activations Density 0.002%

    No Known Activations