© 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. 8150
    Prev
    Next
    INDEX
    Explanations

    options and alternatives

    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
    çĮĹ
    -0.10
    èĤŁ
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    ä¸įåı¯æĢĿ
    -0.08
    æ¤Ł
    -0.08
    mental
    -0.08
    åĬłä¸Ĭ
    -0.08
    éģĩä¸Ĭ
    -0.08
    åĩłä¸ª
    -0.08
    /moment
    -0.08
    POSITIVE LOGITS
    éĥijéĩį
    0.10
     ways
    0.09
     Cornel
    0.09
    解åĨ³
    0.08
    pch
    0.08
    æijĨ
    0.08
     Ways
    0.08
     ÑģобÑģÑĤвенно
    0.08
    çĵ®
    0.08
    éĢĶ
    0.08
    Activations Density 0.229%

    No Known Activations