© 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. 28138
    Prev
    Next
    INDEX
    Explanations

    product discussions

    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
    æł·çļĦ
    -0.10
    ikki
    -0.10
    çªĪ
    -0.09
    çĹħæ¯ĴæĦŁæŁĵ
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    派驻
    -0.09
    thal
    -0.08
    _products
    -0.08
    çĶŁçĶŁ
    -0.08
    é¼ĵèĪŀ
    -0.08
    POSITIVE LOGITS
    vice
    0.10
    ivity
    0.10
    ividad
    0.10
     trÆ°ng
    0.09
    IVITY
    0.09
    çĭĦ
    0.09
    ç¿»å¼Ģ
    0.09
    æĹ©é¤IJ
    0.08
    ç¾
    0.08
    eur
    0.08
    Activations Density 0.030%

    No Known Activations