© 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. 57311
    Prev
    Next
    INDEX
    Explanations

    Code/technical content

    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
    éĿ¢ç§¯
    -0.60
     area
    -0.54
    area
    -0.50
    .area
    -0.49
     Area
    -0.48
    (area
    -0.48
     área
    -0.46
    -area
    -0.46
    _area
    -0.46
    Area
    -0.45
    POSITIVE LOGITS
     Marg
    0.29
    è¢ħ
    0.27
    Marg
    0.27
    otte
    0.27
     pairs
    0.25
     marg
    0.24
    ighbor
    0.24
    adj
    0.24
     Specification
    0.24
     adaptations
    0.24
    Activations Density 0.002%

    No Known Activations