© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    instructions/advice

    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
    hyp
    -0.31
    æŁ¥çľĭåħ¨æĸĩ
    -0.28
    éĶĢ
    -0.27
    èįĴ
    -0.27
    Wik
    -0.26
    ä¼¼çļĦ
    -0.26
    ziej
    -0.25
    éĻ¢å£«
    -0.25
    éļ¾å¾Ĺ
    -0.25
    ä¹ĭç¾İ
    -0.25
    POSITIVE LOGITS
    imens
    0.31
     once
    0.28
    lah
    0.27
    Once
    0.26
    ifique
    0.26
     Once
    0.25
     assure
    0.25
     whole
    0.25
     Ensure
    0.25
    ä¹Łä¸įè¦ģ
    0.25
    Activations Density 0.040%

    No Known Activations