© 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. 33761
    Prev
    Next
    INDEX
    Explanations

    departments and roles

    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
    æĹłåģ¿
    -0.10
    çIJĨäºĭ
    -0.10
    éĺĸ
    -0.10
     Witt
    -0.10
    å¾ĭ
    -0.09
    é«ĺçŃī
    -0.09
    agation
    -0.09
    ülü
    -0.09
    ç¬Ħ
    -0.09
    é¹Ń
    -0.09
    POSITIVE LOGITS
     staff
    0.11
     teams
    0.10
    éĥ¨éŨ
    0.10
     team
    0.10
    åĽ¢éĺŁ
    0.10
     Bet
    0.09
    人åijĺ
    0.09
     department
    0.09
    ĮĢ
    0.08
     Staff
    0.08
    Activations Density 0.148%

    No Known Activations