© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9586
    Prev
    Next
    INDEX
    Explanations

    Cambodia

    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
    æ¤įæłij
    -0.11
    ç§į
    -0.10
    æ°ª
    -0.10
    åľ¨äº¬
    -0.09
    æĦŁåĨĴ
    -0.09
    uers
    -0.09
    çĭ¼
    -0.09
    åģļå¾Ĺ
    -0.09
    uali
    -0.09
    æįħ
    -0.09
    POSITIVE LOGITS
    æŁ¬åŁĶ寨
    0.10
    æļ¹
    0.09
    æ¹Ħ
    0.09
     Cambodia
    0.09
    å»Ĭ
    0.09
    ASE
    0.09
    éľ¹
    0.08
    phis
    0.08
    çļĦç¬ij容
    0.08
     Ph
    0.08
    Activations Density 0.019%

    No Known Activations