© 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. 61314
    Prev
    Next
    INDEX
    Explanations

    aerobic, aerial, aero

    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
    çĶ¨è½¦
    -0.09
    à¹Ĥà¸Ĭ
    -0.09
    çĻĮ
    -0.09
    æĿ²
    -0.09
    ervas
    -0.09
    dır
    -0.08
    身边çļĦ
    -0.08
    笤
    -0.08
    渥
    -0.08
    ÙĬع
    -0.08
    POSITIVE LOGITS
    ally
    0.12
    igm
    0.10
    0.09
    rier
    0.09
    ationally
    0.09
    ne
    0.09
    0
    0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    ically
    0.08
    rière
    0.08
    Activations Density 0.025%

    No Known Activations