© 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. 56790
    Prev
    Next
    INDEX
    Explanations

    any [noun]

    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
    доб
    -0.08
    以å¤ĸ
    -0.08
    å¼ķè¿Ľ
    -0.08
    ä¸ĥæĺŁ
    -0.08
     umb
    -0.07
    oux
    -0.07
    sembl
    -0.07
     NOT
    -0.07
    è¿Ļæł·
    -0.07
    ave
    -0.07
    POSITIVE LOGITS
    ä¸įçĶ±å¾Ĺ
    0.10
    箦
    0.10
    åij±
    0.10
    á»ijc
    0.10
    è°ı
    0.10
    缼åħ¸
    0.10
    æĥľ
    0.10
    éºĴ
    0.10
    ä¸į管
    0.10
    éļĽ
    0.09
    Activations Density 0.037%

    No Known Activations