© 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. 36973
    Prev
    Next
    INDEX
    Explanations

    setting context

    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
    æ³±
    -0.09
    çķ´
    -0.09
    uff
    -0.09
    æºŁ
    -0.09
    éĿ¢åŃIJ
    -0.09
    è·Łä»ĸ
    -0.09
    åĭĥ
    -0.09
     дÑĥÑħ
    -0.09
    åİĺ
    -0.09
    æ²®
    -0.09
    POSITIVE LOGITS
    ä¸Ģè¾¹
    0.10
    æIJģ
    0.09
    ä¸ĢéĤĬ
    0.09
    è¾¹ç¼ĺ
    0.09
    åĤĻ
    0.08
    çĸı
    0.08
    ä¿ĿçķĻ
    0.08
    ãģĸ
    0.08
    çľĭå¾ħ
    0.08
    /place
    0.08
    Activations Density 0.003%

    No Known Activations