© 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. 17671
    Prev
    Next
    INDEX
    Explanations

    advertising and ads

    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
    æĢģ
    -0.10
    hood
    -0.09
    è²Į
    -0.09
    å¾Ĺä¸įåĪ°
    -0.09
    etting
    -0.08
     Reserve
    -0.08
    ettle
    -0.08
    æķ¬è¯·
    -0.08
    esty
    -0.08
     Gardens
    -0.08
    POSITIVE LOGITS
    avn
    0.09
    vertisement
    0.09
    orial
    0.08
    å¾ĹçĽĬ
    0.08
    çĴŀ
    0.08
    å¬Ĺ
    0.08
    -board
    0.08
    æ½ŀ
    0.08
    æĹĦ
    0.08
    符
    0.08
    Activations Density 0.023%

    No Known Activations