© 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. 58269
    Prev
    Next
    INDEX
    Explanations

    now, then, once, already

    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
    ordan
    -0.09
    aney
    -0.09
    èij³
    -0.09
    ÑģмоÑĤÑĢ
    -0.08
    ColorBrush
    -0.08
    à¸ģา
    -0.08
    æīĵçIJĥ
    -0.08
    ieber
    -0.08
    ../../../
    -0.08
    å¹²æ¶ī
    -0.08
    POSITIVE LOGITS
    大æī¹
    0.10
    ç´ł
    0.09
    ä¸Ģ度
    0.09
    iage
    0.08
    fy
    0.08
    ISK
    0.08
    ä¸Ńä»ĭ
    0.08
    å®°
    0.08
    coma
    0.08
    ä¸įåı¯èĥ½
    0.08
    Activations Density 0.039%

    No Known Activations