© 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. 37493
    Prev
    Next
    INDEX
    Explanations

    false and news

    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®Ĭ
    -0.10
    æŁ¥çľĭæĽ´å¤ļ
    -0.10
     undis
    -0.09
    unted
    -0.09
    æ§Ľ
    -0.09
    åĽ½éĻħæľºåľº
    -0.09
    èµĽåĮº
    -0.09
    INU
    -0.08
    å´¦
    -0.08
    å±ķåĮº
    -0.08
    POSITIVE LOGITS
    /il
    0.10
    /false
    0.10
    å¢ŀé«ĺ
    0.09
    ë§IJ
    0.08
    åĢŁåı£
    0.08
    ust
    0.08
    对åѦçĶŁ
    0.08
     Entries
    0.08
    AccessException
    0.08
     Gef
    0.08
    Activations Density 0.080%

    No Known Activations