© 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. 14-TRANSCODER-HP
    7. 40948
    Prev
    Next
    INDEX
    Explanations

    unstructured data / separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Medium
    -0.28
    Medium
    -0.24
    åľ¨ä¸Ģ
    -0.24
    umbo
    -0.24
    ä¾Ľç»Ļ侧
    -0.24
    alloca
    -0.24
     Dur
    -0.23
    -render
    -0.23
    rising
    -0.23
    ertil
    -0.23
    POSITIVE LOGITS
    级以ä¸Ĭ
    0.28
    icas
    0.27
    ieee
    0.26
    çļĦ积æŀģæĢ§
    0.26
    ieties
    0.25
     coaching
    0.25
    ÃľR
    0.25
    建æĪIJåIJİ
    0.25
    urre
    0.24
    积æŀģæĢ§
    0.23
    Activations Density 0.193%

    No Known Activations