© 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. 150276
    Prev
    Next
    INDEX
    Explanations

    connect

    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
     HOLDER
    -0.26
    -eyed
    -0.24
    家éķ¿ä»¬
    -0.24
    prech
    -0.24
     Hayward
    -0.23
     mantle
    -0.23
    PathComponent
    -0.23
    该éĻ¢
    -0.23
    STD
    -0.23
    relative
    -0.23
    POSITIVE LOGITS
    æµģéĩı
    0.30
    icted
    0.29
    æĻºèĥ½
    0.27
    visor
    0.26
    .pb
    0.26
    /sbin
    0.25
     bypass
    0.25
    onium
    0.25
    éĩıåĮĸ
    0.25
    窨
    0.25
    Activations Density 0.112%

    No Known Activations