© 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. 32141
    Prev
    Next
    INDEX
    Explanations

    dopamine or doping agency

    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
    ÑģÑģ
    -0.09
    eing
    -0.09
    沧
    -0.08
    æĶ¾è¿ĩ
    -0.08
    oran
    -0.08
    Õ¦
    -0.08
    nder
    -0.08
    沧æ¡ij
    -0.08
    ç°ª
    -0.08
    éĻĮ
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    æ³¥
    0.10
    çĹ¢
    0.10
    mant
    0.09
    磸
    0.09
    ishly
    0.08
     зÑĢениÑı
    0.08
    ening
    0.08
    yp
    0.08
    itude
    0.08
    Activations Density 0.008%

    No Known Activations