© 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. 11042
    Prev
    Next
    INDEX
    Explanations

    authoritative signals or sources

    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
    å®´
    -0.08
    ع
    -0.08
    paginator
    -0.08
    åij½åIJį
    -0.08
    æĢĿç´¢
    -0.08
    æĢĿ绪
    -0.08
    اÙĩ
    -0.08
    é¹ħ
    -0.08
    à¹Ģà¸ķ
    -0.08
    wash
    -0.08
    POSITIVE LOGITS
    èĢħçļĦ
    0.10
    æĿĥå¨ģ
    0.10
    ONT
    0.09
    ATS
    0.09
    èķ¾
    0.09
    å½ĵå±Ģ
    0.09
     authority
    0.09
     Expert
    0.09
    iveness
    0.09
    ASN
    0.08
    Activations Density 0.005%

    No Known Activations