© 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. 35675
    Prev
    Next
    INDEX
    Explanations

    vulnerable and needy people

    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
    åĴ¯
    -0.09
    åijĹ
    -0.08
    ä¼Ĺ
    -0.08
     Pret
    -0.08
    forced
    -0.08
     Grat
    -0.08
    æĪĸå¤ļ
    -0.08
    rb
    -0.08
    forc
    -0.08
    èĵĵ
    -0.08
    POSITIVE LOGITS
    è®·
    0.10
    æıĨ
    0.10
    arding
    0.10
    æĭIJ
    0.09
    ĮĢ
    0.09
    è§ĴèIJ½
    0.09
    æĪ¾
    0.09
    æŶåĪ»
    0.09
    å¼±åĬ¿
    0.09
    æľĢåŁºæľ¬çļĦ
    0.09
    Activations Density 0.012%

    No Known Activations