© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    comprehensive [topic]

    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
    roc
    -0.11
    çĨł
    -0.09
    isy
    -0.09
    翱
    -0.09
    rames
    -0.09
    ovi
    -0.08
    éŀŃ
    -0.08
    /or
    -0.08
    phan
    -0.08
    é«ĺå±±
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.12
    zza
    0.10
    -minded
    0.10
    rest
    0.09
    lest
    0.09
    æĢĨ
    0.09
    young
    0.09
    oze
    0.09
     luck
    0.08
    çĿĩ
    0.08
    Activations Density 0.024%

    No Known Activations