© 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. 54609
    Prev
    Next
    INDEX
    Explanations

    good qualities or actions

    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
    è®Ń
    -0.08
    ardin
    -0.08
     ob
    -0.08
    移交
    -0.08
    æŃĩ
    -0.08
     Paginator
    -0.08
    移æ¤į
    -0.08
     Salman
    -0.08
    ç»ı
    -0.08
    鸿
    -0.08
    POSITIVE LOGITS
    ä½Ĩåį´
    0.10
    æĮģ
    0.09
    åīįæīĢæľªæľī
    0.09
     Maz
    0.09
    ä¿£
    0.09
    åī½
    0.08
    éĴ»çłĶ
    0.08
    ãģªãģĦãģ¨
    0.08
    å®ŀè´¨
    0.08
    åIJĦç±»
    0.08
    Activations Density 0.051%

    No Known Activations