© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    transitioning through stages

    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
    以æĿ¥
    -0.09
    åįĵ
    -0.09
     extrad
    -0.09
    è·¨åĽ½
    -0.08
    éģ¿
    -0.08
    èĪ
    -0.08
    .enumer
    -0.08
    owe
    -0.08
    课å¤ĸ
    -0.08
    æĪĬ
    -0.08
    POSITIVE LOGITS
    æŃ¥åħ¥
    0.13
    è¿Ľåħ¥
    0.12
    éĢ²åħ¥
    0.12
    è¿Ľåħ¥åĪ°
    0.11
    èµ°åħ¥
    0.10
    è¸ıåħ¥
    0.10
    æľįåĬ¡ä½ĵç³»
    0.10
    çģĮ
    0.09
    转åħ¥
    0.09
    ç¾½
    0.09
    Activations Density 0.096%

    No Known Activations