© 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. 31574
    Prev
    Next
    INDEX
    Explanations

    scrolling down

    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
    зав
    -0.09
    å°¤
    -0.09
     Hutch
    -0.09
    ÑģÑĤеÑĢ
    -0.09
    ChildIndex
    -0.09
    steen
    -0.09
    幸
    -0.08
    lei
    -0.08
    éŨå¤ĸ
    -0.08
    åĬ©
    -0.08
    POSITIVE LOGITS
     scroll
    0.11
     Scroll
    0.09
     scrollTo
    0.09
     brow
    0.09
    	scroll
    0.09
     scrolls
    0.09
    éķ¿éķ¿çļĦ
    0.09
    ertia
    0.09
    ä¸ĭè°ĥ
    0.08
    è½½
    0.08
    Activations Density 0.140%

    No Known Activations