© 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. 17486
    Prev
    Next
    INDEX
    Explanations

    during meiosis

    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
    ouro
    -0.11
    æĥĭ
    -0.11
     Vil
    -0.10
    HeaderCode
    -0.10
    /xhtml
    -0.09
    å¼±çĤ¹
    -0.09
    OSC
    -0.09
    .Val
    -0.09
    dock
    -0.09
    _isr
    -0.09
    POSITIVE LOGITS
     NEC
    0.09
    æĿ¥çļĦ
    0.09
    å¤ĩæĪĺ
    0.08
    éĢļéģĵ
    0.08
    cle
    0.08
     conj
    0.08
    å¾ģéĽĨ
    0.08
    during
    0.08
     during
    0.08
     cle
    0.08
    Activations Density 0.136%

    No Known Activations