© 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. 56747
    Prev
    Next
    INDEX
    Explanations

    person qualities and leadership roles

    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
    _assoc
    -0.09
    æĥ°
    -0.09
    etz
    -0.08
    åĬ©éķ¿
    -0.08
    éĩįè¦ģåĨħ容
    -0.08
    æ¡ĥ
    -0.08
    ylko
    -0.08
    igor
    -0.08
    åĴİ
    -0.08
     beaut
    -0.08
    POSITIVE LOGITS
    å¼ĢæľĹ
    0.16
    æĢ§æł¼
    0.13
    çļĦæĢ§æł¼
    0.12
    åĸĦèī¯
    0.12
    举æŃ¢
    0.11
    ç¬ij容
    0.11
    ç»Ļ人ä¸Ģç§į
    0.11
    å¹½é»ĺ
    0.11
    è¨Ģè¡Į
    0.11
    çĪ½
    0.10
    Activations Density 0.093%

    No Known Activations