© 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. 18038
    Prev
    Next
    INDEX
    Explanations

    account and related actions

    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
    çĭ¡
    -0.09
    -0.08
    æĭŁ
    -0.08
    endale
    -0.08
    itt
    -0.08
    cores
    -0.08
     Monter
    -0.08
    æ¦Ľ
    -0.08
    åĮĹ大
    -0.08
    æľīéĴĪ对æĢ§
    -0.08
    POSITIVE LOGITS
    å´ĸ
    0.11
    ä¸ĢåĪĻ
    0.09
    ROTO
    0.09
    è¡Įäºĭ
    0.09
    梯éĺŁ
    0.09
    벤
    0.09
    åºŃ
    0.09
    夯
    0.09
    ogan
    0.09
    .MEDIA
    0.09
    Activations Density 0.015%

    No Known Activations