© 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. 54643
    Prev
    Next
    INDEX
    Explanations

    processor

    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
    æĢģ
    -0.10
    erd
    -0.09
    ish
    -0.09
    illions
    -0.09
    edi
    -0.09
    éķ³
    -0.09
    ing
    -0.08
    è²Į
    -0.08
     иÑģп
    -0.08
    anio
    -0.08
    POSITIVE LOGITS
    ëĭĺ
    0.09
    -memory
    0.09
    æĹı
    0.09
    etch
    0.08
    ä¸ĢæĹı
    0.08
    æĸĩåĮĸèĬĤ
    0.08
    baugh
    0.08
    çŃĭ
    0.08
    EDURE
    0.08
    iple
    0.08
    Activations Density 0.032%

    No Known Activations