© 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. 57040
    Prev
    Next
    INDEX
    Explanations

    multitasking functions

    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
    ains
    -0.11
    Ñĩик
    -0.09
    ries
    -0.09
    ohn
    -0.08
    çĭ¬
    -0.08
    yard
    -0.08
    FG
    -0.08
    çĭ¬çī¹çļĦ
    -0.08
    æĸ°çļĦ
    -0.08
    etric
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    oom
    0.09
    é«ĺæīĭ
    0.09
    ве
    0.09
    SEA
    0.09
     mage
    0.09
     pur
    0.09
    ç¹ģå¿Ļ
    0.09
    å¾Īå¤ļäºĭæĥħ
    0.09
    èĥ½åĬĽåĴĮ
    0.08
    Activations Density 0.010%

    No Known Activations