© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7589
    Prev
    Next
    INDEX
    Explanations

    childhood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     packed
    -0.26
    åIJİèĢħ
    -0.24
    弹簧
    -0.24
    çģ
    -0.24
    wi
    -0.24
    åİ¿æĶ¿åºľ
    -0.24
    ä¸ĸçķĮåIJĦåľ°
    -0.24
    åľ°ä¸ĭ
    -0.23
    çľ¼æ³ª
    -0.23
    å½ĵåīį
    -0.23
    POSITIVE LOGITS
    ctr
    0.28
    为主é¢ĺçļĦ
    0.27
    èī¯å¥½
    0.26
    ä¸ºåŁºç¡Ģ
    0.25
     ctr
    0.24
    Feb
    0.23
    vre
    0.23
    ением
    0.23
    italize
    0.23
    æł¸å¿ĥåĮº
    0.23
    Activations Density 1.201%

    No Known Activations