© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11859
    Prev
    Next
    INDEX
    Explanations

    closing tag or attribute

    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
    regar
    -0.10
    çĴ¨
    -0.10
    飨
    -0.09
    è¾Ī
    -0.09
     Dod
    -0.09
    aneously
    -0.09
    é»ĺå¥ij
    -0.09
    ope
    -0.09
    æĹĥ
    -0.09
    çĴŁ
    -0.09
    POSITIVE LOGITS
    ...</
    0.09
    ----</
    0.09
    +</
    0.09
    ---</
    0.09
    æµij身
    0.08
    .getState
    0.08
    -</
    0.08
    ua
    0.08
     przec
    0.08
    ä¸ĢæĿ¯
    0.08
    Activations Density 0.494%

    No Known Activations