© 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. 61723
    Prev
    Next
    INDEX
    Explanations

    daily life

    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
    PathComponent
    -0.10
    æľªæĿ¥çļĦ
    -0.09
    æľªæĿ¥
    -0.09
    åīįä¸ī
    -0.08
    èĩ³ä¸Ĭ
    -0.08
    è¿ŀç»Ń
    -0.08
    åľ¨ä¸ĢæĹģ
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
    çīĩéĿ¢
    -0.08
    erte
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»ä¸Ń
    0.13
    ç³Ĭ
    0.09
    -day
    0.08
    ä¸ŃçļĦ
    0.08
    ÐIJв
    0.08
    ä¸Ńãģ«
    0.08
    åħħ
    0.08
    воÑĢ
    0.08
    urger
    0.08
    å·¥ä½ľä¸Ń
    0.08
    Activations Density 0.035%

    No Known Activations