© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    birthday or anniversary

    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
    hare
    -0.09
     Mellon
    -0.09
     smells
    -0.09
    URY
    -0.09
    6
    -0.08
    ERO
    -0.08
    AndWait
    -0.08
    çł´äº§
    -0.08
    ernet
    -0.08
     Transcript
    -0.08
    POSITIVE LOGITS
    为å¥ijæľº
    0.11
    ãĤĴè¿İ
    0.09
    çѵ
    0.09
    á»ĩm
    0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    ä¹ĭéĻħ
    0.09
    bes
    0.09
    åīįå¤ķ
    0.09
     HLS
    0.09
    礼çī©
    0.08
    Activations Density 0.028%

    No Known Activations