© 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. 9173
    Prev
    Next
    INDEX
    Explanations

    refuse to

    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
    å§Ĭ
    -0.08
    ç¡®å®ŀ
    -0.08
    åĪĽæĸ°åŀĭ
    -0.08
    äºĽ
    -0.08
    å¾Ħ
    -0.08
    æķ¬
    -0.08
    åį³å°Ĩ
    -0.08
    orm
    -0.08
    raised
    -0.08
    åĩij
    -0.08
    POSITIVE LOGITS
    ably
    0.12
    ohan
    0.11
    ä¸įèĤ¯
    0.10
    å³
    0.10
    ä¸į让
    0.09
    äºĨåįĬ天
    0.09
    edly
    0.09
    erno
    0.09
    æľīä»»ä½ķ
    0.09
    èĮ¹
    0.09
    Activations Density 0.010%

    No Known Activations