© 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. 3217
    Prev
    Next
    INDEX
    Explanations

    setting out rules

    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
    ivate
    -0.10
    ÑİÑģÑĮ
    -0.09
    igit
    -0.09
    sar
    -0.09
    è¯Ī
    -0.09
    usz
    -0.09
    ihu
    -0.09
    íĥĿ
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    ãĥ¼ãĤº
    -0.08
    POSITIVE LOGITS
    éĥİ
    0.10
    vester
    0.09
    åĿ¦
    0.08
    .Companion
    0.08
    ned
    0.08
    åºŃ
    0.08
    çļĦä¼ĺåĬ¿
    0.08
     plan
    0.08
    éļĨéĩį
    0.08
    äºĨä¸ĢäºĽ
    0.08
    Activations Density 0.010%

    No Known Activations