© 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. 150718
    Prev
    Next
    INDEX
    Explanations

    code snippets/equations

    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
    rovers
    -0.26
    éķĩ
    -0.26
    éħ¸
    -0.26
    uyá»ĩn
    -0.25
    éĨ¢
    -0.25
    rades
    -0.25
    ãģ¼
    -0.25
     Pres
    -0.24
     sized
    -0.24
    ç²¾
    -0.24
    POSITIVE LOGITS
    findFirst
    0.31
    æĹłæīĢ
    0.28
    anon
    0.26
    ä¸Ģå¤Ħ
    0.26
    igers
    0.26
    <Expression
    0.26
    å½³
    0.25
     true
    0.25
    appen
    0.25
    MBER
    0.25
    Activations Density 0.185%

    No Known Activations