© 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. 11682
    Prev
    Next
    INDEX
    Explanations

    negations and intensifiers

    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
    å©ļ纱
    -0.10
    æĢĴ
    -0.10
    gin
    -0.09
    ä¹Łåıªæľī
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    å®ı大
    -0.09
    GIN
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    ä¸įåľ¨
    -0.08
    纶
    -0.08
    POSITIVE LOGITS
    å®Įåħ¨
    0.09
    åĩłä½į
    0.09
    éĺ±
    0.08
    éĺĪ
    0.08
    reh
    0.08
    çĭ®
    0.08
    å®Įåħ¨æĺ¯
    0.08
    ÑĩиÑģÑĤ
    0.08
    tors
    0.08
     Swan
    0.08
    Activations Density 0.026%

    No Known Activations