© 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. 40028
    Prev
    Next
    INDEX
    Explanations

    reports, disclosures, observations

    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
    æĹłåı¯
    -0.28
     dele
    -0.26
    αι
    -0.26
    ä¸įäºĨ
    -0.26
     DK
    -0.25
     Wh
    -0.25
    ç»ĵ论
    -0.25
     па
    -0.25
     PA
    -0.25
    ignet
    -0.25
    POSITIVE LOGITS
    cco
    0.32
    ll
    0.27
    ci
    0.26
    èIJ¥ä¸ļé¢Ŀ
    0.26
    ulu
    0.25
    reads
    0.25
    èĦī
    0.25
    æ´ĭæ´ĭ
    0.25
    мед
    0.24
    CMP
    0.24
    Activations Density 0.134%

    No Known Activations