© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    æłĩçļĦ
    -0.09
    èĸľ
    -0.09
    çŃīçī¹çĤ¹
    -0.09
    åĨľåī¯äº§åĵģ
    -0.09
     courtesy
    -0.08
    è´½
    -0.08
    çŃīå¥ĸ
    -0.08
    é¢Ĩ导人
    -0.08
    -0.08
    åĴĮæľįåĬ¡
    -0.08
    POSITIVE LOGITS
    cipher
    0.09
    æľīæĦıæĢĿ
    0.09
    Äħc
    0.09
    æĬ±çĿĢ
    0.09
    大åıij
    0.09
    oÅĽci
    0.08
    rowned
    0.08
    marsh
    0.08
    æĸ¹æīį
    0.08
    Marsh
    0.08
    Activations Density 0.255%

    No Known Activations