© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    certainly followed by adjectives or verbs

    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
    ãģ¨ãģ«ãģĭãģı
    -0.09
    涵
    -0.09
    ç«ŁçĦ¶
    -0.09
    ä»¿ä½Ľ
    -0.09
    以èĩ³äºİ
    -0.08
    ä¸ŃåįĪ
    -0.08
    éģ½
    -0.08
    åĨįä¹Ł
    -0.08
    lica
    -0.08
    æĪijçĽ¸ä¿¡
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸Ģéĥ¨
    0.12
    æĺ¯ä¸Ģ
    0.11
    第ä¸Ģéĥ¨
    0.10
    eq
    0.10
    æĺ¯ä¸Ģ座
    0.10
    .ids
    0.09
    -not
    0.09
    èģĥ
    0.08
    ANCE
    0.08
    å¼ĢéŨ
    0.08
    Activations Density 0.008%

    No Known Activations