© 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. 37750
    Prev
    Next
    INDEX
    Explanations

    vegetables and veggies

    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
    çĥģ
    -0.09
    é©°
    -0.09
    /generated
    -0.09
    mpr
    -0.09
    tat
    -0.09
    åłĥ
    -0.09
    boo
    -0.08
    SPORT
    -0.08
    羣åĪĩ
    -0.08
    åķ
    -0.08
    POSITIVE LOGITS
     Hayden
    0.10
    iska
    0.10
     Spears
    0.09
    黣
    0.09
    orge
    0.09
    ÑĤе
    0.08
     huyết
    0.08
    arten
    0.08
    chrono
    0.08
    人家
    0.08
    Activations Density 0.008%

    No Known Activations