© 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. 31-TRANSCODER-HP
    7. 19090
    Prev
    Next
    INDEX
    Explanations

    coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aker
    -0.27
     ked
    -0.26
     pragma
    -0.25
     prerequisite
    -0.25
    åĪĨå¼Ģ
    -0.24
    ä¸Ĭ游
    -0.24
     mer
    -0.23
    izer
    -0.23
     Neh
    -0.23
    apel
    -0.23
    POSITIVE LOGITS
    rish
    0.28
    Breadcrumb
    0.26
    æ¶ķ
    0.26
    bish
    0.25
    ómo
    0.24
    çļĦç¡®
    0.24
    è¿ĻåIJį
    0.24
    getState
    0.23
    enting
    0.23
    ılı
    0.23
    Activations Density 60.763%

    No Known Activations