© 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. 51649
    Prev
    Next
    INDEX
    Explanations

    after that

    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
    å½ĵä¸ĭ
    -0.10
    äºİæĺ¯æĪij
    -0.10
    åĪ°è¿ĻéĩĮ
    -0.10
    ä¹į
    -0.09
    ï¸
    -0.09
     вÑĭгод
    -0.09
    /lg
    -0.09
    ities
    -0.09
    æ¯Ķäºļ
    -0.09
    缮çļĦåľ¨äºİ
    -0.09
    POSITIVE LOGITS
    æŁı
    0.09
    à®±
    0.08
    æĩĭ
    0.08
    uda
    0.08
     اÙĦÙĬ
    0.08
    elle
    0.08
    _pf
    0.08
     Dent
    0.08
    ter
    0.08
    åij¢
    0.08
    Activations Density 0.010%

    No Known Activations