© 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. 9640
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    ä¹Łä¸įè¦ģ
    -0.09
    祷
    -0.09
    tips
    -0.09
    æīĭä¸ĭ
    -0.09
    å¥ł
    -0.09
    ä¹Łéĥ½
    -0.09
    管家
    -0.09
    åµ´
    -0.08
    åı¯çĸij
    -0.08
    æĹłæīĢè°ĵ
    -0.08
    POSITIVE LOGITS
    visor
    0.10
    /GPL
    0.08
    ä¹į
    0.08
    åĵį
    0.08
     reverted
    0.08
     ros
    0.08
     Graves
    0.07
    æķħæĦı
    0.07
    /lic
    0.07
    alis
    0.07
    Activations Density 0.253%

    No Known Activations