© 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. 24-TRANSCODER-HP
    7. 150851
    Prev
    Next
    INDEX
    Explanations

    Code, calculations, or data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foot
    -0.29
    <footer
    -0.29
    uby
    -0.28
    足迹
    -0.27
     Shoes
    -0.27
    å±£
    -0.27
    éŀĭ
    -0.26
    å±IJ
    -0.25
    foot
    -0.25
     feet
    -0.25
    POSITIVE LOGITS
    ùng
    0.27
    èĽĽ
    0.25
     deferred
    0.25
    æĬ½
    0.24
    çĶ¨å¾®ä¿¡
    0.24
    iores
    0.24
    oodle
    0.24
    åijĨ
    0.23
    defer
    0.23
    å°Ħ
    0.23
    Activations Density 0.176%

    No Known Activations