© 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. 49762
    Prev
    Next
    INDEX
    Explanations

    cabinet

    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
    æű
    -0.09
    æķĸ
    -0.09
    ocom
    -0.08
     Street
    -0.08
    _CLICKED
    -0.08
    _lengths
    -0.08
    stadt
    -0.08
    æĮ¤
    -0.08
    è¶Ĭéĩİ
    -0.08
     lengths
    -0.08
    POSITIVE LOGITS
    å¼ĢéŨ
    0.12
    pton
    0.11
    çĤĬ
    0.10
    å·¢
    0.10
    Cook
    0.10
    çĥ¹é¥ª
    0.09
    人æĢ§
    0.09
    ä¸ĬéŨ
    0.09
     cuis
    0.09
    .Paths
    0.09
    Activations Density 0.076%

    No Known Activations