© 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. 37464
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
    OLL
    -0.09
    éĿ¢åŃĶ
    -0.09
    ALA
    -0.09
    éĩijéĻµ
    -0.09
    åĴ¬
    -0.09
     demean
    -0.09
    DEM
    -0.09
    bos
    -0.09
    碰
    -0.09
    çĪ¶
    -0.08
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭä¸Ń
    0.09
    asel
    0.08
    åį
    0.08
    è°²
    0.08
     Clarkson
    0.08
    _tail
    0.07
    ä¸Ģæĺ¯
    0.07
    åħ®
    0.07
    æĴ®
    0.07
    asia
    0.07
    Activations Density 0.139%

    No Known Activations