© 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. 61270
    Prev
    Next
    INDEX
    Explanations

    universities like UMBC, Davis, Chicago

    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
    çĭİ
    -0.11
    èĩ»
    -0.10
    æ³¼
    -0.09
    æĥ³ä¸įåĪ°
    -0.08
    NSS
    -0.08
    ä½ĺ
    -0.08
    æĤ²åĵĢ
    -0.08
    uang
    -0.08
    ele
    -0.08
    emente
    -0.08
    POSITIVE LOGITS
    éĢŀ
    0.09
     Decomp
    0.09
    å¥ĭ
    0.08
    æĸ°éĹ»ç½ij
    0.08
    zept
    0.08
    åħ¥åºĵ
    0.08
    asel
    0.08
    .dispatcher
    0.08
    æ·ĸ
    0.08
    æ¦Ī
    0.08
    Activations Density 0.005%

    No Known Activations