© 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. 52568
    Prev
    Next
    INDEX
    Explanations

    a followed by an activity or item

    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
    èĻ
    -0.09
    FromArray
    -0.09
    dated
    -0.09
    æĪķ
    -0.09
     اعت
    -0.08
    plaintext
    -0.08
     permutation
    -0.08
     Mons
    -0.08
    æ¶Įçİ°
    -0.08
    outed
    -0.08
    POSITIVE LOGITS
    brig
    0.10
    _effects
    0.09
    Ñīин
    0.08
    /free
    0.08
    æĦıåij³
    0.08
    antz
    0.08
     bầu
    0.08
     hiá»ĩp
    0.08
    ä¸Ģç«Ļå¼ı
    0.08
    OWL
    0.08
    Activations Density 0.213%

    No Known Activations