© 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. 21558
    Prev
    Next
    INDEX
    Explanations

    things going well or better

    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¯Ł
    -0.09
    侮辱
    -0.09
    åį±éĻ©
    -0.09
    竦
    -0.09
    çŀª
    -0.09
    å¥īçĮ®
    -0.09
    ANI
    -0.09
    åħ³èģĶ
    -0.09
    _residual
    -0.08
    èĤ®
    -0.08
    POSITIVE LOGITS
     дела
    0.11
    è¿Ľå±ķ
    0.10
    ç»ĵæĿŁåIJİ
    0.10
    失åĪ©
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.09
    åıĤ
    0.09
    æĮ«
    0.09
     progress
    0.09
     дело
    0.09
    顺åĪ©
    0.09
    Activations Density 0.042%

    No Known Activations