© 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. 37498
    Prev
    Next
    INDEX
    Explanations

    lwn.net links

    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
    æ¶Ĥ
    -0.09
    èıħ
    -0.08
    reu
    -0.08
    精彩
    -0.08
     buc
    -0.08
    ariant
    -0.07
    çĶŁæĦı
    -0.07
    åIJĪãģĦ
    -0.07
    åİį
    -0.07
     Sr
    -0.07
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.10
    elman
    0.10
    çŃĶåį·
    0.10
    çŃı
    0.09
    ä¸ŃåĽ½å¸Ĥåľº
    0.09
    ussia
    0.09
    isma
    0.09
    çļĤ
    0.09
    alon
    0.09
     Pied
    0.09
    Activations Density 0.005%

    No Known Activations