© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    .org, .services, net

    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
    ited
    -0.09
    æīĵåį¡
    -0.09
    esk
    -0.09
    æ»´æ»´
    -0.08
    ä¸Ģéģĵ
    -0.08
    ocz
    -0.08
     dedicated
    -0.08
    殿ä¸ĭ
    -0.08
    icity
    -0.08
    OfDay
    -0.08
    POSITIVE LOGITS
     dÃłng
    0.11
    ibus
    0.10
    ritos
    0.09
    inition
    0.09
    æĶ½
    0.09
    (DE
    0.09
    ials
    0.09
    ective
    0.09
    endency
    0.09
    å´ĩé«ĺ
    0.09
    Activations Density 1.221%

    No Known Activations