© 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. 57769
    Prev
    Next
    INDEX
    Explanations

    moving on to the next

    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
     sne
    -0.09
    åĬ±
    -0.09
    好å¥ĩå¿ĥ
    -0.09
     Roy
    -0.08
    6
    -0.08
    ReturnValue
    -0.08
    éĵŃ
    -0.08
    æĪijçŁ¥éģĵ
    -0.08
     UTC
    -0.08
    /man
    -0.08
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.13
    ä¸ĭä¸Ģ
    0.12
    åħ¶ä»ĸçļĦ
    0.11
    ä¸ĭä¸Ģç¯ĩ
    0.11
    ä¸ĭä¸ĢæŃ¥
    0.11
    æĽ´éĩįè¦ģçļĦ
    0.10
    åħ¶ä»ĸ
    0.09
    åĪ«çļĦ
    0.09
    æĽ´é«ĺ
    0.09
    åħ¶å®ĥ
    0.09
    Activations Density 0.015%

    No Known Activations