© 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. 36125
    Prev
    Next
    INDEX
    Explanations

    look like, resemblance, appearance

    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
    å¨ĺ家
    -0.10
    åѤ
    -0.10
    åѤçĭ¬
    -0.09
    模æĭŁ
    -0.09
    lords
    -0.09
    onne
    -0.08
    éĩįçİ°
    -0.08
    _collections
    -0.08
    éªĦåĤ²
    -0.08
    äºĴ
    -0.08
    POSITIVE LOGITS
    äºĶå®ĺ
    0.11
    çļĦèĦ¸
    0.11
    身æĿIJ
    0.11
    appearance
    0.10
    人èĦ¸
    0.10
    容è²Į
    0.09
    åı¸
    0.09
    åĻĻ
    0.09
     facial
    0.09
    .shtml
    0.09
    Activations Density 0.068%

    No Known Activations