© 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. 51868
    Prev
    Next
    INDEX
    Explanations

    carry along with

    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
    ENTA
    -0.09
    enta
    -0.09
     pure
    -0.08
    æĤ¬æµ®
    -0.08
    7
    -0.08
    æĮīæŶ
    -0.08
    misc
    -0.08
    5
    -0.08
    éĢīåĩº
    -0.08
     Ace
    -0.08
    POSITIVE LOGITS
    æīĵæĭ¼
    0.11
    æĭįæĭį
    0.10
    绣绣
    0.09
    æİ¥ç§į
    0.09
    _verbose
    0.09
    åİ¥
    0.09
    èĤĥ
    0.09
    onder
    0.09
    çĶ¨å·¥
    0.09
    人åĬĽ
    0.09
    Activations Density 0.047%

    No Known Activations