© 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. 62654
    Prev
    Next
    INDEX
    Explanations

    first ever

    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
    ÙĨÙħ
    -0.10
    é¦ĭ
    -0.10
    alchemy
    -0.09
    OrCreate
    -0.09
     heavens
    -0.09
    åĩłå¹´
    -0.09
    äºĨ好åĩł
    -0.09
    å·²æľī
    -0.09
    å°¤åħ¶
    -0.09
    lah
    -0.08
    POSITIVE LOGITS
    顺
    0.09
    ounce
    0.09
    thing
    0.09
    izen
    0.09
    oline
    0.08
     D
    0.08
    1
    0.08
    æijħ
    0.08
    2
    0.08
    4
    0.08
    Activations Density 0.005%

    No Known Activations