© 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. 37417
    Prev
    Next
    INDEX
    Explanations

    contrast and 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
    å½ĺ
    -0.11
    åı£è¯Ń
    -0.10
     ph
    -0.09
    -answer
    -0.09
    ARP
    -0.09
    .toObject
    -0.09
    ph
    -0.09
    å¤¸å¼ł
    -0.09
    å°±æѤ
    -0.09
     dap
    -0.09
    POSITIVE LOGITS
    忧èĻij
    0.10
    çIJļ
    0.09
    æ·¡æ·¡çļĦ
    0.09
    åĨ·åĨ·
    0.09
    warn
    0.08
    çļĦèĥĮåIJİ
    0.08
    åıĤ
    0.08
    严èĤĥ
    0.08
     tragedy
    0.08
     sober
    0.08
    Activations Density 0.108%

    No Known Activations