© 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. 38761
    Prev
    Next
    INDEX
    Explanations

    to followed by 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
    缴æݥ影åĵį
    -0.09
    ainen
    -0.09
    ucha
    -0.09
    oller
    -0.09
    chia
    -0.09
    zza
    -0.08
    ä½ĵéĩı
    -0.08
    olls
    -0.08
    æĢĿèĢĥ
    -0.08
    .raise
    -0.08
    POSITIVE LOGITS
    å¼Ħ
    0.11
    æĹ©æĹ¥
    0.11
    è¿Ļä¹Īåģļ
    0.11
    尽快
    0.10
    èĥ½å¾ĹåĪ°
    0.10
    èĥ½çľĭåĪ°
    0.10
    æľīæīĢ
    0.10
    äºĨ解
    0.10
    èİ·å¾ĹæĽ´å¤ļ
    0.10
    å¾ĹåĪ°
    0.09
    Activations Density 0.053%

    No Known Activations