© 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. 49319
    Prev
    Next
    INDEX
    Explanations

    asking for, requested that

    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
    ability
    -0.09
    èĨĪ
    -0.08
    fst
    -0.08
    æĹ¥å¸¸å·¥ä½ľ
    -0.08
    него
    -0.08
    afia
    -0.08
    éĢļçŁ¥ä¹¦
    -0.08
    躲éģ¿
    -0.08
    ä¹ħ
    -0.08
    绽
    -0.08
    POSITIVE LOGITS
    å½ĵå±Ģ
    0.12
    å¤ĸçķĮ
    0.10
    åĵĢ
    0.10
    æľªæĪIJ
    0.10
    æ²£
    0.10
    书ä¸Ń
    0.09
    åħ¬ç½ij
    0.09
    表çĻ½
    0.09
    奢ä¾Ī
    0.09
    metro
    0.09
    Activations Density 0.040%

    No Known Activations