© 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. 57435
    Prev
    Next
    INDEX
    Explanations

    benefits of

    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
    åĽŀäºĭ
    -0.11
    ä¸ĢåĽŀäºĭ
    -0.11
    ../../../
    -0.10
    aint
    -0.10
    wers
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    åĬŁå¤«
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    常å§Ķ
    -0.09
    æ¿ĢçĥĪçļĦ
    -0.09
    POSITIVE LOGITS
    fully
    0.12
    aries
    0.11
     nhuáºŃn
    0.10
    ary
    0.10
     ÃŃch
    0.10
    jamin
    0.10
    تر
    0.10
    ARY
    0.09
    æľĢ大åĮĸ
    0.09
     знаÑĤÑĮ
    0.09
    Activations Density 0.027%

    No Known Activations