© 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. 57577
    Prev
    Next
    INDEX
    Explanations

    regular

    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
     traditional
    -0.42
    ä¼łç»Ł
    -0.40
    ä¼łç»ŁçļĦ
    -0.39
     tradition
    -0.39
     traditions
    -0.38
    åĤ³çµ±
    -0.37
     traditionally
    -0.36
     Traditional
    -0.35
    traditional
    -0.35
    Traditional
    -0.35
    POSITIVE LOGITS
     ones
    0.28
    ove
    0.26
     PV
    0.25
     `{
    0.25
     sudoku
    0.25
    gua
    0.25
     pv
    0.25
    æŀ°
    0.25
    (LP
    0.24
    ág
    0.24
    Activations Density 0.009%

    No Known Activations