© 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. 6772
    Prev
    Next
    INDEX
    Explanations

    cooperation and collaboration

    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
    åŃIJéĩĮ
    -0.10
    æ»Ķ
    -0.09
    /or
    -0.09
    ifier
    -0.09
    å¸ĪäºĭåĬ¡æīĢ
    -0.09
    rock
    -0.09
    noch
    -0.09
     dolayı
    -0.08
    建çŃijä¸ļ
    -0.08
    /how
    -0.08
    POSITIVE LOGITS
    geber
    0.10
    ../../../
    0.10
    itus
    0.10
    ðŁı»
    0.09
    Ñĥл
    0.09
    ðŁı¼
    0.09
    .Toolkit
    0.09
    ertino
    0.08
    èĢħçļĦ
    0.08
    ively
    0.08
    Activations Density 0.017%

    No Known Activations