© 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. 54278
    Prev
    Next
    INDEX
    Explanations

    URL parameters

    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
    ç½Ħ
    -0.09
     Regents
    -0.09
    ertz
    -0.09
    å·ħ
    -0.08
    åĿĮ
    -0.08
     далек
    -0.08
    .setter
    -0.08
    allis
    -0.08
    Semaphore
    -0.08
    mania
    -0.07
    POSITIVE LOGITS
    /or
    0.16
    /OR
    0.12
    大家ä¸Ģèµ·
    0.10
    åIJĮæĻĤãģ«
    0.10
    åij¨åĽ´
    0.10
    æ¯ħåĬĽ
    0.09
    æį®æѤ
    0.09
    GINE
    0.09
    å¥ł
    0.09
    uffy
    0.09
    Activations Density 0.656%

    No Known Activations