© 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. 31616
    Prev
    Next
    INDEX
    Explanations

    Zope

    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
    éĥ´å·ŀ
    -0.09
    æĢ»è§īå¾Ĺ
    -0.09
    ays
    -0.09
    ä¸įå°½
    -0.09
    éĻŁ
    -0.08
    æĪ´çĿĢ
    -0.08
    èĩ³æѤ
    -0.08
    ledge
    -0.08
    éĴµ
    -0.08
    ç¼ij
    -0.08
    POSITIVE LOGITS
    ebra
    0.11
    embr
    0.10
    ppelin
    0.10
    pered
    0.10
    unft
    0.09
    illions
    0.09
    ephir
    0.09
    abbix
    0.09
    posium
    0.09
    èĨ¨
    0.09
    Activations Density 0.284%

    No Known Activations