© 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. 30912
    Prev
    Next
    INDEX
    Explanations

    locations ending with on, en, le

    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»ĵ
    -0.09
    åĬłåĢį
    -0.09
    åĴĮ个人
    -0.09
    éĵ¨
    -0.09
    ä½ĵä¼ļ
    -0.09
    æ¿Ģåıij
    -0.08
    åĽ½å®ī
    -0.08
    æĦĶ
    -0.08
    éĿ¢çĻ½
    -0.08
    çĶŁèĤĸ
    -0.08
    POSITIVE LOGITS
    AZY
    0.09
    olk
    0.08
    æľ¬ç½ij
    0.08
    å°Ĭ
    0.08
    sse
    0.08
    åĵĵ
    0.08
     FSM
    0.08
    à¹Ģว
    0.08
    _compat
    0.08
    rz
    0.07
    Activations Density 0.383%

    No Known Activations