© 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. 52604
    Prev
    Next
    INDEX
    Explanations

    evaluation of outcomes

    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
    严
    -0.09
    /inc
    -0.09
    дал
    -0.09
    éļĥ
    -0.09
    åīįæīĢæľª
    -0.08
     заÑīиÑĤ
    -0.08
    عرب
    -0.08
     Rig
    -0.08
    ock
    -0.08
    åIJijå¾Ģ
    -0.08
    POSITIVE LOGITS
    è°ĥåij³
    0.11
    çģµæ°Ķ
    0.10
    ExecutionContext
    0.10
    ä¸Ģéĥ¨
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    çļĦæĦŁæĥħ
    0.10
    æĸ¯é¡¿
    0.10
    æĦŁäºº
    0.10
    æĦŁæĥħ
    0.10
    çĬ
    0.09
    Activations Density 0.065%

    No Known Activations