© 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. 20939
    Prev
    Next
    INDEX
    Explanations

    `getSuit`, `Source`, `targets`, `connecting`

    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
    溢
    -0.11
    ç»ıéªĮ丰å¯Į
    -0.10
    _defs
    -0.09
     collaps
    -0.09
    nett
    -0.09
     Fach
    -0.09
    ç¿»
    -0.08
    æłĩéħį
    -0.08
    ضة
    -0.08
    akit
    -0.08
    POSITIVE LOGITS
    ä½ľåĵģåĨħ容
    0.10
    éĤ£ä¸ªæŶåĢĻ
    0.09
    ãģĦãģij
    0.09
    çįIJ
    0.09
    FIX
    0.09
    ç¬ķ
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    åıĭ
    0.09
    å¹²äºĭ
    0.08
    æİĮæı¡
    0.08
    Activations Density 0.195%

    No Known Activations