© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52792
    Prev
    Next
    INDEX
    Explanations

    ridiculous and ludicrous words

    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
    ICY
    -0.08
    LOY
    -0.08
    inge
    -0.08
    lain
    -0.08
    IDI
    -0.08
    æģ¬
    -0.08
    人èĦ¸
    -0.08
    æŀķ
    -0.08
     Dav
    -0.08
    jee
    -0.08
    POSITIVE LOGITS
    ulous
    0.11
    ably
    0.11
    оÑģÑĮ
    0.11
    ous
    0.10
    /il
    0.10
     amounts
    0.10
    ness
    0.10
    诮
    0.10
    ITY
    0.10
    uous
    0.09
    Activations Density 0.007%

    No Known Activations