© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50390
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities followed by lists/sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĻĭ
    -0.08
     gou
    -0.08
    Ctx
    -0.08
    ount
    -0.08
    s
    -0.08
    g
    -0.08
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.08
     politic
    -0.07
    rier
    -0.07
    shake
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸įæķ¢
    0.10
    ä¸Ģ对
    0.10
    è¿Ļä¹Łæĺ¯
    0.09
     à¸Ļà¸Ńà¸ģà¸Īาà¸ģ
    0.09
    åĮĹæµ·
    0.09
    _SLAVE
    0.09
    ç¿Į
    0.09
    alus
    0.09
    é¹ķ
    0.09
     serialVersionUID
    0.09
    Activations Density 0.170%

    No Known Activations