© 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. 49497
    Prev
    Next
    INDEX
    Explanations

    announcement of results or choices

    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¿ĩåİ»çļĦ
    -0.08
    è¿ĽæĿ¥
    -0.08
     seemingly
    -0.08
    è¿Ľåħ¥äºĨ
    -0.08
    rose
    -0.08
    è¿İæĿ¥äºĨ
    -0.08
    PHA
    -0.08
    èĥĮåIJİ
    -0.08
    åĩºçİ°äºĨ
    -0.08
    åĽłä¸º
    -0.08
    POSITIVE LOGITS
    å±ĬæŶ
    0.16
    åĪ°æŶåĢĻ
    0.12
    .final
    0.10
    æľĢç»Ī
    0.10
    éĢīåĩº
    0.10
     лÑĥÑĩÑĪиÑħ
    0.10
    æĺİå¹´
    0.10
    æĭ©
    0.10
    æľĢçµĤ
    0.10
    å¼Ģå¥ĸ
    0.09
    Activations Density 0.047%

    No Known Activations