© 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. 23920
    Prev
    Next
    INDEX
    Explanations

    "peace be" / "(zl)." / "t/a" / "d/b"

    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
    å¤ĸéĿ¢
    -0.09
    æį¢äºĨ
    -0.09
    æį¢
    -0.09
    åĨħå¤ĸ
    -0.08
     Mana
    -0.08
    äºĴèģĶäºĴéĢļ
    -0.08
    anging
    -0.08
    ä½łä»¥ä¸º
    -0.08
    Outside
    -0.08
    æĽ¼
    -0.08
    POSITIVE LOGITS
    олов
    0.11
    IFT
    0.10
    NST
    0.09
    弩
    0.09
    é¢ĦåijĬ
    0.09
    è®°å¿ĨåĬĽ
    0.09
    åijIJ
    0.09
    åŃĹåı·
    0.09
    Scalars
    0.09
    eled
    0.09
    Activations Density 0.107%

    No Known Activations