© 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. 36653
    Prev
    Next
    INDEX
    Explanations

    not followed by a descriptor

    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
    çŀĴ
    -0.11
    RELEASE
    -0.09
    æ¥ł
    -0.09
    าà¸ĩ
    -0.08
    çĩ®
    -0.08
    tee
    -0.08
    .timing
    -0.08
    æĬľ
    -0.08
     Prest
    -0.08
    èĤī
    -0.08
    POSITIVE LOGITS
    æĭį
    0.10
    æĽ¿ä»£
    0.10
     пÑĢедназнаÑĩен
    0.09
    ä¸įåı¯ä»¥
    0.09
    泫
    0.08
    ä¸įæĺ¯ä¸Ģ个
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.08
    æ»ŀ
    0.08
    icks
    0.08
    åį§
    0.08
    Activations Density 0.043%

    No Known Activations