© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    avoid + verb

    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
    ening
    -0.09
    æķijåij½
    -0.09
    REE
    -0.09
    稳
    -0.09
    -old
    -0.09
    hem
    -0.09
     ÄIJá»ĵng
    -0.09
    URING
    -0.09
    uben
    -0.08
    irling
    -0.08
    POSITIVE LOGITS
    ance
    0.14
    ances
    0.13
    ANCE
    0.12
    ä¸įäºĨ
    0.11
    ably
    0.10
    ä¹ĭæĺŁ
    0.09
     иÑģполÑĮзованиÑı
    0.09
    讳
    0.09
    äºĨä¸Ģåľº
    0.09
     Äijâu
    0.09
    Activations Density 0.020%

    No Known Activations