© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61155
    Prev
    Next
    INDEX
    Explanations

    MAC, Kat Von D, long-lasting eye shadows

    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¸ĸçķĮè§Ĥ
    -0.11
    èĢģçĪ·
    -0.11
    åıijçİ°éĹ®é¢ĺ
    -0.09
    å¼ķæµģ
    -0.09
    æ¶Īæ¯Ĵ
    -0.09
    rels
    -0.09
    ä¸įèĪĴæľį
    -0.08
    æ·Ļ
    -0.08
    qus
    -0.08
    RC
    -0.08
    POSITIVE LOGITS
    æű
    0.09
    indi
    0.09
    amel
    0.08
    æĭ¢
    0.08
    çŁ¿çī©è´¨
    0.08
    fax
    0.08
    çĩ¥
    0.08
     visite
    0.08
    æĴij
    0.08
    产åѦ
    0.08
    Activations Density 0.011%

    No Known Activations