© 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. 57619
    Prev
    Next
    INDEX
    Explanations

    area measurements

    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
    åĮ¿åIJį
    -0.26
    truncate
    -0.26
     truncate
    -0.25
    ilinear
    -0.25
    åĿIJåľ¨
    -0.24
     Intercept
    -0.24
    OI
    -0.24
    uchos
    -0.24
    oris
    -0.24
    IAS
    -0.24
    POSITIVE LOGITS
    çĸĨ
    0.28
    æ¶Ľ
    0.27
    æµ·åŁŁ
    0.26
     Dare
    0.26
    èĮĥåĽ´
    0.25
    å®Ŀè´µ
    0.24
    Sugar
    0.24
    ZONE
    0.24
    <body
    0.24
     Range
    0.24
    Activations Density 0.001%

    No Known Activations