© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56492
    Prev
    Next
    INDEX
    Explanations

    rules, commands, laws

    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
    obil
    -0.09
    æł¹æºIJ
    -0.09
    é«ĺä½İ
    -0.09
    çĴľ
    -0.09
    (argument
    -0.09
    å©ķ
    -0.09
     lá»Ļ
    -0.09
    ijľ
    -0.09
    usan
    -0.08
    梵
    -0.08
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.20
     rules
    0.20
    rules
    0.19
    æ³ķåĪĻ
    0.18
    rule
    0.17
     rule
    0.17
    å®ļå¾ĭ
    0.16
    Rules
    0.15
    _rules
    0.15
    .rules
    0.15
    Activations Density 0.101%

    No Known Activations