© 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. 40194
    Prev
    Next
    INDEX
    Explanations

    born

    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
    iras
    -0.35
    BERS
    -0.27
    ApplicationBuilder
    -0.27
    ira
    -0.24
     holland
    -0.24
    berman
    -0.23
    bery
    -0.23
    haul
    -0.23
    izioni
    -0.23
    çłĶ究åijĺ
    -0.23
    POSITIVE LOGITS
    è¡¥é½IJ
    0.28
    ç»ıå¼Ģ
    0.27
     matched
    0.25
    æݨåĩºäºĨ
    0.25
    æŁ
    0.25
     Crest
    0.25
     kü
    0.25
    Qual
    0.25
    æŀķ头
    0.24
    -License
    0.24
    Activations Density 0.129%

    No Known Activations