© 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. 38394
    Prev
    Next
    INDEX
    Explanations

    dressed up

    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
    ä¸Ģæ³¢
    -0.09
    鸥
    -0.09
    regon
    -0.09
    caff
    -0.09
    å§ļ
    -0.09
    åĪ°æŶåĢĻ
    -0.09
     мног
    -0.09
    воз
    -0.09
    lew
    -0.08
    ä½ĵè´¨
    -0.08
    POSITIVE LOGITS
    橱
    0.10
    åĸľ
    0.09
    éħļ
    0.08
    æ²¹èĦĤ
    0.08
    ambre
    0.08
    _MARKER
    0.08
    marker
    0.08
    ATUS
    0.08
    髦
    0.08
    红æĺŁ
    0.08
    Activations Density 0.024%

    No Known Activations