© 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. 7533
    Prev
    Next
    INDEX
    Explanations

    soldering

    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
    ç²īç¢İ
    -0.10
    åıĪ好
    -0.10
    æ¤įæłij
    -0.09
    .nlm
    -0.09
    arda
    -0.08
     Carlson
    -0.08
    褰
    -0.08
    èĪĢ
    -0.08
     Vulner
    -0.08
    èĻĵ
    -0.08
    POSITIVE LOGITS
    ç¬ı
    0.10
    大èĩ£
    0.09
     kå
    0.09
    大åŁİå¸Ĥ
    0.09
    åħħ足çļĦ
    0.09
    æłĢ
    0.09
    éĩįå¤§é¡¹çĽ®
    0.08
     wax
    0.08
    åħīæ»ij
    0.08
    åŁİå¸Ĥåıijå±ķ
    0.08
    Activations Density 0.005%

    No Known Activations