© 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. 18057
    Prev
    Next
    INDEX
    Explanations

    selected items

    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
    sey
    -0.11
    ì§ľ
    -0.10
    ä¾Ŀçħ§
    -0.09
    éŃĶ
    -0.09
    akest
    -0.08
    ound
    -0.08
    èĩªèº«çļĦ
    -0.08
    èĩ³äºİ
    -0.08
    éģij
    -0.08
    seys
    -0.08
    POSITIVE LOGITS
    èªł
    0.10
    è¯ļ
    0.09
    éĤ¦
    0.09
     Pall
    0.09
    [selected
    0.09
    åĩłå®¶
    0.09
    (selected
    0.09
     зап
    0.09
    åľ©
    0.08
    /all
    0.08
    Activations Density 0.041%

    No Known Activations