© 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. 1642
    Prev
    Next
    INDEX
    Explanations

    here to help

    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
     Elli
    -0.10
    åľ¨æł¡
    -0.10
    овÑĭй
    -0.09
    æµģæĺŁ
    -0.09
    åĩºéŨ
    -0.09
    ãģĦãģ¾
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    èĭij
    -0.09
    åľ¨ä¸Ģèµ·
    -0.09
    æ»ļ
    -0.09
    POSITIVE LOGITS
     полож
    0.08
    asted
    0.08
    heet
    0.08
    èĮ¬
    0.08
     misd
    0.08
    lesen
    0.08
    _pad
    0.08
     pad
    0.08
     pylint
    0.08
    émon
    0.07
    Activations Density 0.169%

    No Known Activations