© 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. 48463
    Prev
    Next
    INDEX
    Explanations

    Western corrected visual

    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
    容å¿į
    -0.10
    аÑģÑĤ
    -0.09
    éĹ»
    -0.09
    matic
    -0.08
    isy
    -0.08
    å¤ĩçĶ¨
    -0.08
     Covered
    -0.08
    æī¶
    -0.08
    USED
    -0.08
    istine
    -0.08
    POSITIVE LOGITS
    onga
    0.10
    åĬłä¹ĭ
    0.08
    çĿ«æ¯Ľ
    0.08
    绾
    0.08
    èģĶ缣
    0.08
    ld
    0.08
    顶éĥ¨
    0.08
    åĬłä¸Ĭ
    0.08
    çłĶ究ä¸Ńå¿ĥ
    0.08
     Raz
    0.08
    Activations Density 0.003%

    No Known Activations