© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5934
    Prev
    Next
    INDEX
    Explanations

    season

    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
    _slope
    -0.10
    æī£
    -0.10
    é£Łçī©
    -0.10
    _HOR
    -0.09
    Credits
    -0.09
    çĩĥæĸĻ
    -0.09
    REA
    -0.09
    slope
    -0.08
    oko
    -0.08
     Credits
    -0.08
    POSITIVE LOGITS
    ä¸įçIJĨ
    0.09
    åIJİæŀľ
    0.09
    æľīçļĦ人
    0.09
    å§Ĵ
    0.08
    å¸ĥå°Ķ
    0.08
    æĢı
    0.08
     Sachs
    0.08
     bisher
    0.07
    yar
    0.07
    è¿Ń
    0.07
    Activations Density 0.016%

    No Known Activations