© 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. 150090
    Prev
    Next
    INDEX
    Explanations

    heart

    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
    creens
    -0.26
     wegen
    -0.25
    Rated
    -0.25
     Rai
    -0.24
    åĽł
    -0.24
     Legs
    -0.24
    çIJĨæĻº
    -0.24
     zach
    -0.24
    ETS
    -0.23
    plotlib
    -0.23
    POSITIVE LOGITS
    egade
    0.26
    emp
    0.26
    ìĬµ
    0.25
    çģ¯
    0.25
    panic
    0.25
    ocracy
    0.24
    åģ¿
    0.24
    æł¸å¿ĥæĬĢæľ¯
    0.24
    ump
    0.24
    -core
    0.24
    Activations Density 0.071%

    No Known Activations