© 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. 62697
    Prev
    Next
    INDEX
    Explanations

    video game titles and publishers

    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
    гÑĥ
    -0.10
    upal
    -0.10
    åľ°æ®µ
    -0.09
     Homes
    -0.09
    æģį
    -0.09
     Furn
    -0.09
    ENER
    -0.09
    çŁ¥èŃĺ
    -0.09
    æĥ®
    -0.09
    uhl
    -0.09
    POSITIVE LOGITS
     sequ
    0.09
     PC
    0.08
    PC
    0.08
    	pc
    0.08
     pc
    0.08
    _At
    0.08
     sequel
    0.08
    ä¸Ĭå¸Ĥ
    0.08
    å¥ĺ
    0.08
     Pc
    0.08
    Activations Density 0.263%

    No Known Activations