© 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. 22505
    Prev
    Next
    INDEX
    Explanations

    template-free

    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
    åĺ§
    -0.10
    velt
    -0.10
    xca
    -0.10
    鸵
    -0.10
    èķĻ
    -0.10
    ardon
    -0.10
    ypy
    -0.09
    aty
    -0.09
    ynn
    -0.09
    èįīåľ°
    -0.09
    POSITIVE LOGITS
    第äºĮæī¹
    0.09
    post
    0.09
     legend
    0.09
    ðĿĶ½
    0.08
    4
    0.08
     Friedman
    0.08
    æİĴåĪĹ
    0.08
    5
    0.08
    uro
    0.08
    æį
    0.08
    Activations Density 0.176%

    No Known Activations