© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51885
    Prev
    Next
    INDEX
    Explanations

    Share the Journey

    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
    æ¹Ł
    -0.10
    _Vert
    -0.09
    è¿ŀè¿ŀ
    -0.09
    大éĩı
    -0.09
    å¹ħ
    -0.08
    ):-
    -0.08
    _GPU
    -0.08
    жи
    -0.08
    解æķ£
    -0.08
    หว
    -0.08
    POSITIVE LOGITS
    è°´è´£
    0.09
    é«ĺ峰论åĿĽ
    0.09
    omatic
    0.08
    æĭĴ
    0.08
    çĢ
    0.08
    æĺ¯ä¸ºäºĨ
    0.08
    麻çĹ¹
    0.08
    æĬĽå¼ĥ
    0.08
    enna
    0.08
    ört
    0.08
    Activations Density 0.100%

    No Known Activations