© 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. 39150
    Prev
    Next
    INDEX
    Explanations

    ignore

    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
    æݪ
    -0.09
     ÑĢазнÑĭÑħ
    -0.09
    åİĭ缩
    -0.09
    usercontent
    -0.09
    isis
    -0.09
    _HAL
    -0.09
    è§ģè¯Ĩ
    -0.09
     Surprise
    -0.09
    è¶ģçĿĢ
    -0.09
    izi
    -0.09
    POSITIVE LOGITS
    çļĦåŃĺåľ¨
    0.09
    (ignore
    0.09
     возможноÑģÑĤÑĮ
    0.09
    ä»¥äººä¸ºæľ¬
    0.09
    å·´åŁº
    0.09
     altogether
    0.09
    碴
    0.09
    ä¸Ģå¿ĥ
    0.08
    llib
    0.08
    忽çķ¥äºĨ
    0.08
    Activations Density 0.046%

    No Known Activations