© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21031
    Prev
    Next
    INDEX
    Explanations

    will or should followed by verbs

    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
    æ·±çŁ¥
    -0.12
    空çĻ½
    -0.10
    ç»·
    -0.10
    å¿ĥä¸ŃçļĦ
    -0.09
     Brush
    -0.09
    æĢµ
    -0.09
    даеÑĤÑģÑı
    -0.09
     brush
    -0.09
    éĻ¡
    -0.09
    umper
    -0.09
    POSITIVE LOGITS
    åľ¨å½ĵåľ°
    0.10
    干活
    0.10
    åıijåħī
    0.09
    ä¸ŃåIJ«æľī
    0.09
    immel
    0.09
    äº
    0.09
    å¹Ħ
    0.09
    oa
    0.08
    åij³éģĵ
    0.08
    çī¹çĤ¹æĺ¯
    0.08
    Activations Density 0.266%

    No Known Activations