© 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. 55375
    Prev
    Next
    INDEX
    Explanations

    frequency and regularity

    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
    éºĵ
    -0.10
    ä»ĬæĻļ
    -0.10
    çIJĨ
    -0.10
    离
    -0.09
    KIT
    -0.09
    åŁĶ
    -0.09
    åı«æĪij
    -0.08
    NL
    -0.08
     Yourself
    -0.08
    ä¸Ģå¾ĭ
    -0.08
    POSITIVE LOGITS
    ogg
    0.10
    æѦåĬŁ
    0.10
    åĽ½åĨħå¤ĸ
    0.10
    è¾ĩ
    0.09
    åħ¬åijĬ
    0.09
    ä¸įå®ļ
    0.09
    æĶ¶åĽŀ
    0.09
    éĥ½ä¼ļæľī
    0.09
    æīĢæıIJä¾Ľ
    0.09
    å¾ģéĽĨ
    0.09
    Activations Density 0.052%

    No Known Activations