© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 39998
    Prev
    Next
    INDEX
    Explanations

    contact us

    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
    çε士
    -0.09
    submitted
    -0.09
    ãģĴ
    -0.08
    èĦĤ
    -0.08
    è¡ĮåĬ¨è®¡åĪĴ
    -0.08
    被æ·ĺæ±°
    -0.08
    æł·çļĦ
    -0.08
    çĥĽ
    -0.08
    itud
    -0.08
    å¸Ĥ人大
    -0.08
    POSITIVE LOGITS
    äºĮèĢħ
    0.10
    bies
    0.10
    åĩĨ
    0.09
    æľīä»»ä½ķ
    0.09
    æīĢåľ¨çļĦ
    0.09
    اÙħا
    0.09
    amac
    0.09
    æĮĩåįĹ
    0.08
    رÙĨ
    0.08
    بط
    0.08
    Activations Density 0.011%

    No Known Activations