© 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. 31005
    Prev
    Next
    INDEX
    Explanations

    use of

    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
    æĸ°çļĦä¸Ģ
    -0.11
    çłĶ究éĻ¢
    -0.11
    çĪ¶åŃIJ
    -0.10
    å±ķæľĽ
    -0.10
    ÑģÑĤÑĢел
    -0.09
    imu
    -0.09
    çľ¼ç§ij
    -0.09
    太å°ij
    -0.09
    çģµéŃĤ
    -0.09
    ixon
    -0.09
    POSITIVE LOGITS
     ability
    0.08
    .par
    0.08
     tendency
    0.08
    çĪ¬ä¸Ĭ
    0.08
    ipse
    0.08
     mere
    0.08
    Wind
    0.08
    Begin
    0.08
    alian
    0.07
    è´§æŀ¶
    0.07
    Activations Density 0.130%

    No Known Activations