© 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. 28036
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    ãģķãģĪ
    -0.12
    uso
    -0.10
    ä¿Ł
    -0.10
    DOCUMENT
    -0.10
    éĹŃ
    -0.09
    OrNull
    -0.09
    æģŃåĸľ
    -0.09
    èµ·çłģ
    -0.09
    çľĭçĶµå½±
    -0.08
    æįĨç»ij
    -0.08
    POSITIVE LOGITS
    æľīè¿Ļæł·çļĦ
    0.11
    è¿ĩå¾Ģ
    0.10
    åįķä¸Ģ
    0.09
     artificial
    0.09
    æİł
    0.08
    çī¹å®ļ
    0.08
    éĤ£ä½į
    0.08
    人工
    0.08
    ElementException
    0.08
    大åĬĽ
    0.08
    Activations Density 0.043%

    No Known Activations