© 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. 8679
    Prev
    Next
    INDEX
    Explanations

    court case identifiers

    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
    éĺħ读åħ¨æĸĩ
    -0.12
    åĪį
    -0.10
    buzz
    -0.10
    æģķ
    -0.10
    WSC
    -0.10
    æĭ¿èµ·
    -0.10
    åįģ足
    -0.10
    屯
    -0.10
    åķ¬
    -0.09
    註
    -0.09
    POSITIVE LOGITS
    æ¡©
    0.09
    西çıŃ
    0.08
    çŃīä¸Ģæī¹
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
    çīµ
    0.08
    åīįçŀ»
    0.07
    äºĮåįģå¹´
    0.07
     prelim
    0.07
    -slide
    0.07
    Attachment
    0.07
    Activations Density 0.620%

    No Known Activations