© 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. 54344
    Prev
    Next
    INDEX
    Explanations

    best rental prices

    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
    èĩªè´Ł
    -0.10
     cá»Ń
    -0.10
    uja
    -0.10
    ä¸Ĭå²Ĺ
    -0.09
    artner
    -0.09
    .Groups
    -0.09
    åѤçĭ¬
    -0.08
    ãģĬäºĴ
    -0.08
    èķ»
    -0.08
    unda
    -0.08
    POSITIVE LOGITS
    麽
    0.09
    áŀĴ
    0.09
    çĽĺ
    0.08
    æľ«
    0.08
    åłª
    0.08
    vit
    0.08
     vit
    0.08
    .tk
    0.08
    羸
    0.08
    é¢Ŀ
    0.08
    Activations Density 0.001%

    No Known Activations