© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21792
    Prev
    Next
    INDEX
    Explanations

    mos followed by suffixes

    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
    uate
    -0.10
    æ¤Ĵ
    -0.10
    ãĤ·ãĥ§ãĥ³
    -0.09
    幡
    -0.09
    abet
    -0.09
    çŀ©çĽ®
    -0.09
    çĸļ
    -0.09
    éªĦ
    -0.08
    ìĸ¼
    -0.08
    ãĤıãĤĬ
    -0.08
    POSITIVE LOGITS
    matic
    0.13
    ì§ģ
    0.11
    ambique
    0.11
    irth
    0.10
    bles
    0.10
    moz
    0.10
    aic
    0.10
    agne
    0.10
    ingly
    0.10
    yth
    0.10
    Activations Density 0.022%

    No Known Activations