© 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. 51194
    Prev
    Next
    INDEX
    Explanations

    fork

    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
    bout
    -0.10
    æħµ
    -0.09
    pecially
    -0.09
    atron
    -0.09
    éĩijåŃĹ
    -0.09
    portun
    -0.08
    åħ¥åı£
    -0.08
    æ°ijæĹı
    -0.08
    ç£ģåľº
    -0.08
    annel
    -0.08
    POSITIVE LOGITS
     Esc
    0.10
    iers
    0.10
    éĻ©
    0.10
    Esc
    0.10
    å¨ij
    0.09
    escaping
    0.09
    INAL
    0.08
    马æĭī
    0.08
    èݱ
    0.08
    æµĬ
    0.08
    Activations Density 0.047%

    No Known Activations