© 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. 29789
    Prev
    Next
    INDEX
    Explanations

    actuation or actuator

    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
    审
    -0.10
    åĽŀéģ¿
    -0.09
    åīľ
    -0.09
    æĪIJå°±
    -0.09
    iled
    -0.08
    审è§Ĩ
    -0.08
    Ľå»º
    -0.08
    æĪĺçķ¥æĢ§
    -0.08
    åı²è¯Ĺ
    -0.08
    çļĦæĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    æľºæŀĦ
    0.11
    æ©Łæ§ĭ
    0.11
    åħ³èĬĤ
    0.11
    æĶ¶åĽŀ
    0.11
    åĪ°ä½į
    0.11
    åĬ¨åĬĽ
    0.10
    èģĶåĬ¨
    0.10
    åĬ¨ä½ľ
    0.10
    ymes
    0.10
    çļĦåĬ¨åĬĽ
    0.10
    Activations Density 0.251%

    No Known Activations