© 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. 17692
    Prev
    Next
    INDEX
    Explanations

    to be one of

    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
    rew
    -0.08
     ju
    -0.08
    åĵĪå°Ķ
    -0.08
     наб
    -0.07
    éĩį建
    -0.07
    defer
    -0.07
    串
    -0.07
    åı¦
    -0.07
    oney
    -0.07
    红æĹĹ
    -0.07
    POSITIVE LOGITS
    æľī两个
    0.10
    ળ
    0.10
    æķŀå¼Ģ
    0.10
    ðŁĵĺ
    0.10
    ä¹Łå¥½
    0.09
    å¥ł
    0.09
    ayı
    0.09
     wsp
    0.09
    –↵↵
    0.09
    terra
    0.09
    Activations Density 0.022%

    No Known Activations