© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    on a footing

    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
    åĥĩ
    -0.08
    ä¹ĭæĪĺ
    -0.08
    ãĤ«ãĥĥãĥĹ
    -0.08
    æ´ŀ
    -0.08
    urat
    -0.08
    .jet
    -0.08
    ä¹İ
    -0.08
    OTO
    -0.07
     kept
    -0.07
    lemn
    -0.07
    POSITIVE LOGITS
    èµĦæĸĻæĺ¾ç¤º
    0.10
    onomy
    0.10
    åĨįçİ°
    0.09
    izo
    0.09
    èįĨ
    0.09
    æģŃ
    0.09
    çŃĩ
    0.09
    eds
    0.09
    TypeID
    0.08
    轨éģĵ
    0.08
    Activations Density 0.036%

    No Known Activations