© 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. 29521
    Prev
    Next
    INDEX
    Explanations

    mathematics and science

    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
     hom
    -0.26
    groupBox
    -0.25
    ussy
    -0.24
    åįĩéĻį
    -0.23
    preset
    -0.23
    æĮ¯ãĤĬ
    -0.23
    æĵį纵
    -0.23
     запиÑģи
    -0.23
    uen
    -0.23
     manip
    -0.23
    POSITIVE LOGITS
    ÑĨиÑı
    0.24
     createContext
    0.24
    hoot
    0.24
     Há
    0.24
    road
    0.23
    irmed
    0.23
    åħ¬è·¯
    0.23
    lict
    0.23
    åįİå°Ķè¡Ĺ
    0.23
    åįķä½į
    0.22
    Activations Density 3.829%

    No Known Activations