© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    supporters and followers

    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
     اÙĦدÙĨÙĬا
    -0.11
    çķĻå®Ī
    -0.09
    rolled
    -0.09
    ÑĥÑĤÑĮ
    -0.09
    åĬ©çIJĨ
    -0.08
    озв
    -0.08
    olle
    -0.08
    åIJĮä»ģ
    -0.08
    æ¹¾
    -0.08
     Ñģобой
    -0.08
    POSITIVE LOGITS
    hip
    0.14
    éĴ±è´¢
    0.10
    ł
    0.10
    sWith
    0.10
    çĥŃè®®
    0.09
    amel
    0.09
    ãģĮãĤī
    0.09
    ниÑĨа
    0.09
    lege
    0.09
    çĭİ
    0.09
    Activations Density 0.010%

    No Known Activations