© 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. 17348
    Prev
    Next
    INDEX
    Explanations

    Buckley LJ, Merrill Lynch

    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
    ed
    -0.10
    æĪij认为
    -0.09
    ONSE
    -0.08
    ì¹ĺ
    -0.08
    azing
    -0.08
    iting
    -0.08
    ìĥģìĿĦ
    -0.07
    åĸı
    -0.07
    游ä¹IJ
    -0.07
    å®°
    -0.07
    POSITIVE LOGITS
    issa
    0.10
    è¨ĢãģĪãģ°
    0.09
    isque
    0.09
    nier
    0.09
    icle
    0.09
    ìį¨
    0.09
    aced
    0.08
    ibrated
    0.08
    ync
    0.08
    aded
    0.08
    Activations Density 0.001%

    No Known Activations