© 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. 11171
    Prev
    Next
    INDEX
    Explanations

    native software or extensions

    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
    èĩ³å°Ĭ
    -0.09
    eler
    -0.09
    ä¸įæĪIJ
    -0.09
    åıªä¸º
    -0.09
    æĪIJåĬŁçļĦ
    -0.09
    atsu
    -0.09
    产ä¸ļéĽĨèģļ
    -0.08
    åIJįæł¡
    -0.08
    åĪłéĻ¤æĪIJåĬŁ
    -0.08
    æĺĶæĹ¥
    -0.08
    POSITIVE LOGITS
    /native
    0.11
    æģķ
    0.10
    -born
    0.10
    unda
    0.09
    itas
    0.09
    /manual
    0.08
    ubs
    0.08
     native
    0.08
    asha
    0.08
    ely
    0.08
    Activations Density 0.035%

    No Known Activations