© 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. 9-TRANSCODER-HP
    7. 29739
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĽæĦı
    -0.26
    лиÑĨ
    -0.26
    èķĻ
    -0.25
     labour
    -0.25
    LAB
    -0.24
    æ·¹
    -0.24
    åĬ³åĬ¨
    -0.24
    Labour
    -0.24
    ktor
    -0.23
    posable
    -0.23
    POSITIVE LOGITS
    æĩ
    0.28
    asts
    0.28
    볨
    0.27
     Marl
    0.26
    æī¿
    0.26
     serialVersionUID
    0.25
    Bear
    0.25
    IRE
    0.25
    iben
    0.24
    ç»Ĵ
    0.24
    Activations Density 8.754%

    No Known Activations