© 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. 22103
    Prev
    Next
    INDEX
    Explanations

    website is

    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
    ately
    -0.11
    ément
    -0.11
    western
    -0.10
    åĪ¶æĪIJ
    -0.10
    /write
    -0.09
    intosh
    -0.09
    åįģ足
    -0.09
    itional
    -0.09
    wel
    -0.09
    ìĤ¬íķŃ
    -0.09
    POSITIVE LOGITS
    sockets
    0.10
    eker
    0.09
    à¹Ħà¸ĭ
    0.09
    ÙĤات
    0.08
    ÙĪغ
    0.08
    inars
    0.08
    豪
    0.08
    /blog
    0.08
    ãģĩ
    0.08
    èľĴ
    0.08
    Activations Density 0.049%

    No Known Activations