© 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. 4871
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    ties
    -0.12
    ãģ¤ãģ®
    -0.10
    tte
    -0.10
    uko
    -0.10
    onor
    -0.09
    ropp
    -0.09
    ä¸ĩå¤ļ
    -0.09
    åľª
    -0.09
    cient
    -0.09
    rium
    -0.08
    POSITIVE LOGITS
    æµģè¡ĮçļĦ
    0.10
    çļĦåĬªåĬĽ
    0.10
    æıIJåĩºçļĦ
    0.09
    å½¼
    0.08
    å½¢åĬ¿
    0.08
    owi
    0.08
    âĶĦ
    0.07
    æĻĤçĤ¹
    0.07
    à¤Ł
    0.07
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.07
    Activations Density 0.315%

    No Known Activations