© 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. 49721
    Prev
    Next
    INDEX
    Explanations

    spoke to

    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
    StartPosition
    -0.09
    iane
    -0.09
    说åĩºæĿ¥
    -0.09
    etti
    -0.09
    ç¢į
    -0.09
    å¿ħè¦ģçļĦ
    -0.08
    éĿ¢ç²ī
    -0.08
     Ptr
    -0.08
    avery
    -0.08
    åĽĽçº§
    -0.08
    POSITIVE LOGITS
     why
    0.09
    为ä½ķ
    0.09
    Utility
    0.09
    å¦Ĥä½ķ
    0.08
    å¦Ĥä½ķåİ»
    0.08
    ento
    0.08
    elsey
    0.08
     how
    0.08
    åĩŃ
    0.08
    æĪ·åı£
    0.08
    Activations Density 0.010%

    No Known Activations