© 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. 23476
    Prev
    Next
    INDEX
    Explanations

    select, enter, return

    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
    äºĨä¸Ģä¼ļ
    -0.09
    lus
    -0.09
    _tc
    -0.09
    æľ¬èº«
    -0.08
    ilt
    -0.08
    /MIT
    -0.08
    _timing
    -0.07
    Jur
    -0.07
    æŃ»è§Ĵ
    -0.07
    .Angle
    -0.07
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.09
    并éĢļè¿ĩ
    0.09
    çĦ¶åIJİ
    0.09
    æĤ¬
    0.08
    æĪ³
    0.08
    éħįä¸Ĭ
    0.08
    åĮħåĮħ
    0.08
     tá»Ļi
    0.08
    åħ±äº«åįķ车
    0.08
    ä¼łåĩº
    0.08
    Activations Density 0.128%

    No Known Activations