© 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. 40041
    Prev
    Next
    INDEX
    Explanations

    diverse text data

    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
    è¿Ļä¸Ģ次
    -0.33
     дÑĥÑħ
    -0.27
    è¾Ī
    -0.27
    cken
    -0.26
    ressing
    -0.26
    è¿Ļ次
    -0.25
    -serving
    -0.24
     Members
    -0.24
    ÈĻi
    -0.24
     Sandwich
    -0.24
    POSITIVE LOGITS
    >\<^
    0.27
    çļĦèģĮä¸ļ
    0.26
    idl
    0.25
    лик
    0.25
    éĦ£
    0.25
     dial
    0.25
    ativ
    0.25
    liv
    0.24
    %^
    0.24
     drill
    0.24
    Activations Density 1.460%

    No Known Activations