© 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. 20-TRANSCODER-HP
    7. 63612
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨįåİ»
    -0.26
    ä¹Ŀé¾Ļ
    -0.26
    opol
    -0.26
    privileged
    -0.26
    æĪij们çļĦ
    -0.25
     Caul
    -0.25
    edly
    -0.24
    Catch
    -0.24
    lap
    -0.24
    maal
    -0.24
    POSITIVE LOGITS
    åľ¨åŃ¦æł¡
    0.28
     san
    0.26
    (_.
    0.25
    å¹´ä¹ĭ
    0.25
    æ¿Ģæ´»
    0.25
    ivic
    0.25
    æķ°æį®åºĵ
    0.25
    çļĦæ¯Ķä¾ĭ
    0.24
     lo
    0.23
    çĽĪ
    0.23
    Activations Density 13.510%

    No Known Activations