© 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. 61019
    Prev
    Next
    INDEX
    Explanations

    past participles followed by "by"

    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
    笳
    -0.09
    为æѤ
    -0.08
    åĮ¹
    -0.08
    å±ŀå®ŀ
    -0.08
    è§ĦåĪĴ建设
    -0.08
    æı¡ä½ı
    -0.08
    æĤłæĤł
    -0.08
    éĢij
    -0.08
    RLF
    -0.08
    ä¸ªå·¥ä½ľæĹ¥
    -0.08
    POSITIVE LOGITS
    åıĹ
    0.10
    强çĥĪ
    0.10
    åıĹåĪ°
    0.10
    强çĥĪçļĦ
    0.09
    -license
    0.09
    gia
    0.09
    _INF
    0.09
    çļĦçī¹çĤ¹
    0.08
    æĦ§
    0.08
    _PARAMETERS
    0.08
    Activations Density 0.106%

    No Known Activations