© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    dampen or reduce vibration

    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
    ä¸įä¸ĭ
    -0.11
    æīģ
    -0.10
    å¾Ĺèµ·
    -0.09
    éĿ¢è²Į
    -0.09
    èµ·çĤ¹
    -0.09
    ë©Ģ
    -0.09
    iolet
    -0.09
    æĿĥå¨ģ
    -0.09
    å°Ħ
    -0.09
    éĽī
    -0.08
    POSITIVE LOGITS
     damping
    0.12
    æ»ŀ
    0.11
    illos
    0.11
    åĩıå¼±
    0.10
    åĮĸ解
    0.10
    ç¼ĵåĨ²
    0.09
    ç¼ĵ
    0.09
    æŁĶæĢ§
    0.09
    åīĬå¼±
    0.09
    å¹³éĿĻ
    0.09
    Activations Density 0.097%

    No Known Activations