© 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. 34964
    Prev
    Next
    INDEX
    Explanations

    physical or mailing addresses

    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
    ê¹IJ
    -0.10
    eness
    -0.09
    otify
    -0.09
    åĩºå±Ģ
    -0.09
    essage
    -0.08
    ously
    -0.08
    strate
    -0.08
    ars
    -0.08
    izen
    -0.08
    bling
    -0.08
    POSITIVE LOGITS
    edly
    0.13
    ses
    0.12
    ials
    0.10
    ional
    0.10
    åİ¢
    0.10
    sing
    0.10
    way
    0.09
    миÑĢ
    0.09
    ãĥ¡ãĥ³ãĥĪ
    0.09
    ioned
    0.09
    Activations Density 0.019%

    No Known Activations