© 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. 36741
    Prev
    Next
    INDEX
    Explanations

    end/wrap up

    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
    quals
    -0.10
    æĵį
    -0.10
     Dominion
    -0.10
    ãĥĢ
    -0.10
    поÑĤ
    -0.10
    ç¹ĩ
    -0.10
    æ´»ä¸ĭåİ»
    -0.10
     Stopwatch
    -0.09
    缸çĪ±
    -0.09
    æģ¤
    -0.09
    POSITIVE LOGITS
    ç»ĵæĿŁäºĨ
    0.13
    å®Įç»ĵ
    0.09
    ä¸Ģéĥ¨åĪĨ
    0.09
    è¿Ļä½į
    0.09
    ç»ĵæĿŁ
    0.09
    7
    0.09
    9
    0.08
    åľĨ满
    0.08
    ä¹ĭéĻħ
    0.08
     conclusion
    0.08
    Activations Density 0.036%

    No Known Activations