© 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. 23480
    Prev
    Next
    INDEX
    Explanations

    extent to which

    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
    æĤļ
    -0.10
    å¥ı
    -0.09
    å½ĵä»ĸ
    -0.09
    å®°
    -0.09
    éĹ°
    -0.09
    èĬĤæ°´
    -0.09
    æĹłæīĢè°ĵ
    -0.09
    媳å¦ĩ
    -0.09
    èĭĮ
    -0.09
    çļĦ羣å®ŀæĢ§
    -0.09
    POSITIVE LOGITS
    çĥĤ
    0.09
    æijĺ
    0.08
    nano
    0.08
    .setMaximum
    0.08
    ikt
    0.08
     Revel
    0.08
    .Ret
    0.08
    ä¸ĩåįĥ
    0.08
     rock
    0.08
    åľ°ä¸Ńæµ·
    0.08
    Activations Density 0.001%

    No Known Activations