© 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. 33908
    Prev
    Next
    INDEX
    Explanations

    cognitive function, behavioral, impairment, bias

    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
    inder
    -0.10
    åŁ¹
    -0.09
    ents
    -0.09
     ÑħоÑĤÑı
    -0.08
    {}",
    -0.08
    ter
    -0.08
    rack
    -0.08
    inois
    -0.08
    oux
    -0.08
    èij¡èIJĦ
    -0.08
    POSITIVE LOGITS
    ledged
    0.12
    çĹĩ
    0.11
    失è°ĥ
    0.10
    ears
    0.10
    æĸ¹éĿ¢çļĦ
    0.09
    举æŃ¢
    0.09
    tte
    0.09
     اÙĦجÙħع
    0.09
    åĩłæŃ¥
    0.09
     ìķĦëĭĮ
    0.09
    Activations Density 0.039%

    No Known Activations