© 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. 18273
    Prev
    Next
    INDEX
    Explanations

    nickname

    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
    æĿµ
    -0.10
    èĭ
    -0.09
    ä½ıåľ¨
    -0.09
    çĶļ
    -0.08
    èĮ«èĮ«
    -0.08
    ÑģÑĤÑĢоен
    -0.08
    ĥģ
    -0.08
    ä¸ĢåĪ»
    -0.08
    äºĮåįģåĽĽ
    -0.08
    3
    -0.08
    POSITIVE LOGITS
    ature
    0.09
    åĽ¢
    0.09
    åĪ«
    0.09
    è°¿
    0.09
    æļ
    0.09
    AndPassword
    0.09
    ãĥĭãĥ¼
    0.08
    (Roles
    0.08
    çĪ±åIJĥ
    0.08
    æĺµ
    0.08
    Activations Density 0.049%

    No Known Activations