© 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. 35174
    Prev
    Next
    INDEX
    Explanations

    light, signaling, fog, marked, court, shadow

    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
    éĹ·
    -0.10
    éĶ¦ç»£
    -0.10
    èIJ±
    -0.09
    ÑĤин
    -0.09
    æĭ¿ä¸ĭ
    -0.09
    éĬ·
    -0.09
    çªģåĩ»
    -0.09
    èĥĮ
    -0.09
     SWAT
    -0.09
    éĿĽ
    -0.09
    POSITIVE LOGITS
    ighthouse
    0.10
    æĺı
    0.09
    priv
    0.09
    èĮħ
    0.09
    .accuracy
    0.09
    æĦļ
    0.09
    -course
    0.08
    ä¿¡åı·
    0.08
    éĻ¤
    0.08
     ActiveRecord
    0.08
    Activations Density 0.046%

    No Known Activations