© 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. 50191
    Prev
    Next
    INDEX
    Explanations

    opposition and criticism

    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
     Loft
    -0.08
     Lomb
    -0.08
     Chin
    -0.08
    ENA
    -0.08
    asy
    -0.08
    ä¼ĺåħĪ
    -0.07
    mate
    -0.07
    referrer
    -0.07
    aman
    -0.07
     ponder
    -0.07
    POSITIVE LOGITS
    认为
    0.11
    è¹Ļ
    0.11
    è§īå¾Ĺ
    0.10
    deo
    0.10
    æīĢåľ¨åľ°
    0.10
    åĽłä¸ºæĪij
    0.10
    说æĪij
    0.10
    æĢ»è§īå¾Ĺ
    0.10
    ä¸į满
    0.09
    驹
    0.09
    Activations Density 0.061%

    No Known Activations