© 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. 4521
    Prev
    Next
    INDEX
    Explanations

    also other

    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
    ISTA
    -0.11
    ä»ĭ
    -0.10
    èĢĮä¸įæĺ¯
    -0.10
    icter
    -0.09
    æĹ¢è¦ģ
    -0.09
    æĸ°ä¸Ģ代
    -0.09
    æĪĸ许æĺ¯
    -0.09
     кли
    -0.09
    ista
    -0.09
    笥
    -0.09
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.15
    åħ¶å®ĥ
    0.13
     other
    0.12
    ä¾ĭå¤ĸ
    0.10
    åĪ«çļĦ
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    ä¹Łä¼ļ
    0.10
     outras
    0.10
    _other
    0.09
     outros
    0.09
    Activations Density 0.183%

    No Known Activations