© 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. 21424
    Prev
    Next
    INDEX
    Explanations

    conference sessions, workshops, speakers, presentations

    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
    ç»Į
    -0.08
    éĻIJãĤĬ
    -0.08
    uzu
    -0.08
    豸
    -0.08
     Piet
    -0.08
    è±Ĩ
    -0.08
    èĥĮ
    -0.08
    riot
    -0.08
    顺
    -0.08
    ichel
    -0.08
    POSITIVE LOGITS
    ä¸ĬåįĪ
    0.12
    åħ¨å¤©
    0.11
    æĹ¶æ®µ
    0.11
    ä¸ĭåįĪ
    0.11
    干货
    0.11
     afternoon
    0.10
     sessions
    0.10
    精彩
    0.10
    精彩çļĦ
    0.10
    ä¸ĭåįĬåľº
    0.10
    Activations Density 0.040%

    No Known Activations