© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50821
    Prev
    Next
    INDEX
    Explanations

    upstairs, downstairs, backstage, tailor-made

    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
    -0.11
    bery
    -0.09
    寸
    -0.09
    æł¸åĩĨ
    -0.09
    issen
    -0.09
    ary
    -0.08
    stones
    -0.08
    å®ŀäºĭæ±Ĥæĺ¯
    -0.08
    è¾½å®ģ
    -0.08
    _tac
    -0.08
    POSITIVE LOGITS
    .await
    0.09
    lid
    0.09
    çĮ¶
    0.08
     Diy
    0.08
    å¥Ķ
    0.08
    à¹Īà¸Ń
    0.08
    侬
    0.08
    çĬ¹
    0.08
    çĹĽ
    0.08
    pons
    0.08
    Activations Density 0.003%

    No Known Activations