© 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. 49071
    Prev
    Next
    INDEX
    Explanations

    continue after 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
    çĮĿ
    -0.10
    quam
    -0.09
    çıª
    -0.09
    gom
    -0.09
    海滨
    -0.09
    CRET
    -0.09
    edith
    -0.08
     пеÑĢе
    -0.08
    lots
    -0.08
    çݯç»ķ
    -0.08
    POSITIVE LOGITS
    æ¸IJæ¸IJ
    0.10
    çĥ¦
    0.10
    å¿ĥ头
    0.10
    人å¿ĥ
    0.10
    æĦŁ
    0.10
    èĬ¥
    0.09
    æī°
    0.09
    ucked
    0.09
    ç¥ŀç»ı
    0.09
    çĥ¦èºģ
    0.09
    Activations Density 0.069%

    No Known Activations