© 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. 30737
    Prev
    Next
    INDEX
    Explanations

    granting permission or rights

    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
    -0.12
    ä¸įå®ļ
    -0.09
    icity
    -0.09
    -transitional
    -0.09
    ARAM
    -0.09
    ota
    -0.09
    ownik
    -0.08
    å°¼äºļ
    -0.08
    combe
    -0.08
    äºĭåIJİ
    -0.08
    POSITIVE LOGITS
     access
    0.10
    Ģ
    0.09
    forma
    0.09
    listed
    0.09
    emain
    0.09
    ained
    0.09
    /dis
    0.08
    æĥ³è±¡
    0.08
    MLS
    0.08
    ship
    0.08
    Activations Density 0.027%

    No Known Activations