© 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. 31356
    Prev
    Next
    INDEX
    Explanations

    by virtue of

    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
    éĴ®
    -0.09
    ibling
    -0.09
    iment
    -0.09
    äºī
    -0.09
    rear
    -0.09
    ilet
    -0.09
    ivate
    -0.09
    æķħäºĭ
    -0.08
    仲
    -0.08
    imei
    -0.08
    POSITIVE LOGITS
    大家éĥ½åľ¨
    0.10
    å¼łè´´
    0.09
    _singular
    0.09
    ãģĿãĤĮãģĮ
    0.09
    åħ¶
    0.09
     being
    0.09
    æİĴ
    0.08
     having
    0.08
     its
    0.08
    å¾Ĺ天çĭ¬åİļ
    0.08
    Activations Density 0.012%

    No Known Activations