© 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. 30-TRANSCODER-HP
    7. 95473
    Prev
    Next
    INDEX
    Explanations

    settle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yll
    -0.29
    å±ı
    -0.27
    /manual
    -0.26
    çĢļ
    -0.26
    æݳ
    -0.25
    enal
    -0.25
    ongsTo
    -0.24
    è¿ĩåħ³
    -0.24
    å¼ķåıijäºĨ
    -0.24
    CLUSIVE
    -0.24
    POSITIVE LOGITS
    ownt
    0.33
     smoothly
    0.31
     Life
    0.29
     successfully
    0.29
     Pend
    0.29
    亲
    0.29
     within
    0.28
    åľ¨æķ´ä¸ª
    0.28
     securely
    0.27
     politely
    0.27
    Activations Density 0.891%

    No Known Activations