© 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. 9189
    Prev
    Next
    INDEX
    Explanations

    electrical conductivity

    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
    éĻĮçĶŁäºº
    -0.10
    è§Į
    -0.09
    åŀ«
    -0.09
    pel
    -0.09
     Kaiser
    -0.08
    æīĭæ³ķ
    -0.08
    ICLE
    -0.08
    çĸı
    -0.08
    otes
    -0.08
    éĿ¢åħ·
    -0.08
    POSITIVE LOGITS
    _unc
    0.09
    æ¡£
    0.09
    Affected
    0.09
    è·¨
    0.09
    ·¨
    0.09
    æ»´æ»´
    0.09
    渡
    0.09
    è·¨è¶Ĭ
    0.08
    åįĹåĮĹ
    0.08
    åIJ¸çĥŁ
    0.08
    Activations Density 0.374%

    No Known Activations