© 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. 32677
    Prev
    Next
    INDEX
    Explanations

    polling and polls

    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
    al
    -0.08
    ment
    -0.08
    ibility
    -0.07
    IMER
    -0.07
     pac
    -0.07
    åĵŁ
    -0.07
    åĩŃåĢŁ
    -0.07
    对å¤ĸ
    -0.07
    åı
    -0.07
     pd
    -0.07
    POSITIVE LOGITS
    ä¿İ
    0.10
    æİĸ
    0.10
    æĹłç§ģ
    0.10
    æĥľ
    0.10
    åĻ¼
    0.10
    otics
    0.09
    æĶ»åĿļ
    0.09
    山路
    0.09
    å±ī
    0.09
    棣
    0.09
    Activations Density 0.003%

    No Known Activations