© 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. 51995
    Prev
    Next
    INDEX
    Explanations

    hook and loop fasteners

    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
    æĺİå¹´
    -0.09
    èĥĮä¸Ĭ
    -0.09
    .getIn
    -0.09
    åĵĢ
    -0.09
    æĿ²
    -0.08
    çľ¼åīį
    -0.08
    =back
    -0.08
    виÑĤ
    -0.08
    éĢłèĪ¹
    -0.08
    -pos
    -0.08
    POSITIVE LOGITS
    çĹķ
    0.10
     snag
    0.09
     Weinstein
    0.09
    éĴ©
    0.09
    æĮĤçĿĢ
    0.09
    éĴ§
    0.09
    çīµæĮĤ
    0.09
    ÅĤu
    0.09
    avn
    0.09
    ä½ıäºĨ
    0.09
    Activations Density 0.087%

    No Known Activations