© 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. 31680
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
    енно
    -0.10
    ква
    -0.09
    æıIJåīį
    -0.09
    äºĭåħĪ
    -0.09
    æ§Į
    -0.09
    åĪ»èĭ¦
    -0.09
    toa
    -0.09
    åıijè´¢
    -0.08
    lick
    -0.08
    arel
    -0.08
    POSITIVE LOGITS
    éĢ¡
    0.10
    åĪĽ
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    æĭħè´Ł
    0.09
    çĶļèĩ³æĺ¯
    0.08
    èĩĥ
    0.08
    decision
    0.08
    æīįåıijçİ°
    0.08
    å½ĵæĪij们
    0.08
     lifestyle
    0.08
    Activations Density 0.027%

    No Known Activations