© 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. 10447
    Prev
    Next
    INDEX
    Explanations

    legal action and allegations

    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
    Guy
    -0.09
    æĮ¯åħ´
    -0.09
    éĹ®éĹ®
    -0.09
     stip
    -0.08
     Fors
    -0.08
     Bon
    -0.08
    ç§īæī¿
    -0.08
    icide
    -0.08
    åİ»çľĭçľĭ
    -0.08
    åıģ
    -0.08
    POSITIVE LOGITS
    .assertThat
    0.09
    å±¹
    0.09
    apur
    0.09
    æŃ¢
    0.09
    lis
    0.09
    çªģå¦Ĥåħ¶
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    tera
    0.09
    æĪIJæľ¬
    0.09
    æĹ¢è¦ģ
    0.09
    Activations Density 0.058%

    No Known Activations