© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 35234
    Prev
    Next
    INDEX
    Explanations

    will/’ll followed by a verb

    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
    为äºĨ让
    -0.11
    éĥ½è¦ģ
    -0.10
    æĪij们è¦ģ
    -0.09
    è¿ĺè¦ģ
    -0.09
    è¿Ļä¹Ī
    -0.09
    æľªèĥ½
    -0.08
    ald
    -0.08
    åıĪè¦ģ
    -0.08
    å¿ħé¡»è¦ģ
    -0.08
    éĢłæĪIJäºĨ
    -0.08
    POSITIVE LOGITS
    æĽ´å®¹æĺĵ
    0.17
    å°±ä¸įä¼ļ
    0.15
    ä½łä¼ļ
    0.12
    èĩªçĦ¶èĢĮçĦ¶
    0.11
    æĽ´å¥½åľ°
    0.11
    å°±ä¼ļ
    0.11
    æĽ´èĥ½
    0.11
    ä½łä¼ļåıijçݰ
    0.10
    ä¼ļæľī
    0.10
    æľīæĽ´å¥½çļĦ
    0.10
    Activations Density 0.060%

    No Known Activations