© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38537
    Prev
    Next
    INDEX
    Explanations

    Annie, Maggie, University, nap

    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
    ç¿¡
    -0.10
    ening
    -0.10
    Elite
    -0.10
    ettle
    -0.09
    ç»ıæŁ¥
    -0.09
    大æĪĺ
    -0.09
    iers
    -0.09
    reen
    -0.09
    ean
    -0.09
    éĿĵ
    -0.09
    POSITIVE LOGITS
    åĭĩæ°Ķ
    0.09
    istra
    0.09
    ниÑĨ
    0.08
    _variation
    0.08
    isl
    0.08
    bers
    0.08
    ä¸İæŶ
    0.08
    tering
    0.08
    èĪ
    0.08
    variation
    0.08
    Activations Density 0.003%

    No Known Activations