© 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. 27926
    Prev
    Next
    INDEX
    Explanations

    LXQt, MC, mail, Ubuntu, ufw

    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
    泯
    -0.09
    é²ľèī³
    -0.09
    æµģ转
    -0.08
    è¿ĺä¸įå¦Ĥ
    -0.08
    rote
    -0.08
    äºĶæĺŁ
    -0.08
    urd
    -0.08
    åĬĽè¿ĺæĺ¯
    -0.08
    åĽŀäºĭ
    -0.08
    çĽij管éĥ¨éŨ
    -0.08
    POSITIVE LOGITS
    pector
    0.09
    ä¸ĵ线
    0.09
    çĶļèĩ³
    0.09
    æ´¾
    0.09
    æĴij
    0.08
    'article
    0.08
    æ¯ĭ
    0.08
    ×ĸ×Ķ
    0.08
    å°Ĭ
    0.08
    .CreateCommand
    0.08
    Activations Density 0.007%

    No Known Activations