© 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. 30866
    Prev
    Next
    INDEX
    Explanations

    nurture, nursing,

    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
    am
    -0.09
     ton
    -0.09
    AndPassword
    -0.09
    大çīĩ
    -0.09
    æĶ¯
    -0.08
    оÑģоб
    -0.08
    æī°ä¹±
    -0.08
    /or
    -0.08
    dio
    -0.08
    ire
    -0.08
    POSITIVE LOGITS
    æĪIJéķ¿ä¸º
    0.14
    壮大
    0.11
    icism
    0.10
    bate
    0.10
    maid
    0.10
    èĢĮæĪIJ
    0.09
    æľŁåĨħ
    0.09
    ä¸Ģä¸ĭ
    0.09
    oga
    0.09
    posix
    0.09
    Activations Density 0.003%

    No Known Activations