© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    documentation blocks

    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
    avar
    -0.09
    é©·
    -0.09
    以èĩ³äºİ
    -0.08
    å¼Ģæľº
    -0.08
    æ¡ħ
    -0.08
    ByPrimaryKey
    -0.08
    æ¹Ķ
    -0.08
    çĻ»ä¸Ĭ
    -0.08
    /misc
    -0.08
    ViewById
    -0.08
    POSITIVE LOGITS
    ĶåĽŀ
    0.09
    æĹģ
    0.09
    æĤ²åī§
    0.08
    对ä»ĸ
    0.08
    æĺŃ
    0.08
    è°¦
    0.08
    ra
    0.08
    çĸij
    0.08
     Kendall
    0.08
    æī«
    0.08
    Activations Density 0.242%

    No Known Activations