© 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. 60965
    Prev
    Next
    INDEX
    Explanations

    former titles, people, locations

    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
    ç¼Ń
    -0.10
    åѦçĶŁä»¬
    -0.10
    æıIJéĨĴ
    -0.10
    æĥº
    -0.09
    arro
    -0.08
     muddy
    -0.08
    æıIJ示
    -0.08
    询
    -0.08
    ilight
    -0.08
    æĥħ人èĬĤ
    -0.08
    POSITIVE LOGITS
    æĽ¾ä»»
    0.13
    çĨŁæĤī
    0.13
    åĩºèº«
    0.12
    ç»ıéªĮ丰å¯Į
    0.12
    æ¯ķä¸ļäºİ
    0.11
    ç±į
    0.11
    éĻŁ
    0.11
    ç²¾éĢļ
    0.11
    åѦåİĨ
    0.10
    æĩĤ
    0.10
    Activations Density 0.144%

    No Known Activations