© 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. 30608
    Prev
    Next
    INDEX
    Explanations

    timeline, calendar, sheet, API, event

    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
    nable
    -0.10
    è¾ĸ
    -0.09
    ible
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    èį¦
    -0.09
    NING
    -0.08
    ulum
    -0.08
    pile
    -0.08
    æĻĸ
    -0.08
    ä¸ī级
    -0.08
    POSITIVE LOGITS
    -like
    0.10
    è¢ĭ
    0.09
    å·¥ä½ľèĢħ
    0.09
    etary
    0.09
    笥
    0.09
    enty
    0.08
    ï¸ı
    0.08
    ги
    0.08
    ç¢İçīĩ
    0.08
    家å±ħ
    0.08
    Activations Density 0.021%

    No Known Activations