© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    damn near everything

    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
    eks
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.09
    åĿŀ
    -0.08
    å¸ĺ
    -0.08
    岩
    -0.08
    æľªå©ļ
    -0.08
    æĥ°
    -0.08
    åĽ½æĥħ
    -0.08
    å¹²èĦĨ
    -0.08
    erer
    -0.08
    POSITIVE LOGITS
    对æīĭ
    0.11
    cheng
    0.10
    èĴ²
    0.10
    cy
    0.10
    ç«ŀäºī对æīĭ
    0.09
    onga
    0.09
    çĪ±ä¸Ĭ
    0.09
    íľ´
    0.09
    roperties
    0.08
    éķĶ
    0.08
    Activations Density 0.001%

    No Known Activations