© 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. 31756
    Prev
    Next
    INDEX
    Explanations

    katy and katie variations

    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
    ваÑĢ
    -0.10
    riendly
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    åİŁæłĩé¢ĺ
    -0.09
    بÙĥ
    -0.08
    ered
    -0.08
    rapper
    -0.08
    otel
    -0.08
    تÙĦ
    -0.08
    curring
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.12
     phá»ij
    0.10
    enger
    0.09
    kok
    0.09
    èĩªå¦Ĥ
    0.09
    sburg
    0.09
    elper
    0.09
    rees
    0.08
    说å®ŀè¯Ŀ
    0.08
     Peyton
    0.08
    Activations Density 0.005%

    No Known Activations