© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51435
    Prev
    Next
    INDEX
    Explanations

    superlative completion of "ever"

    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
    soon
    -0.09
    ãģ¨ãĤĤ
    -0.09
    åĨĴ
    -0.09
     Prime
    -0.09
    ModelProperty
    -0.08
    å´İ
    -0.08
    éĿŀè¦ģ
    -0.08
    人人éĥ½
    -0.08
    åħį
    -0.08
    æ¯ı个人éĥ½
    -0.08
    POSITIVE LOGITS
    theless
    0.10
    åĬłæĮģ
    0.09
    æĥľ
    0.09
    åIJĪå½±
    0.09
    åıijå±ķä¸Ń
    0.09
    究
    0.09
    è§Į
    0.09
    ç¶ļãģı
    0.09
    æĥħåĨµè¿Ľè¡Į
    0.09
     encount
    0.09
    Activations Density 0.023%

    No Known Activations