© 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. 18789
    Prev
    Next
    INDEX
    Explanations

    have or own

    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
    çĶ³æĬ¥
    -0.09
     Barbar
    -0.08
    èįĴ
    -0.08
     MenuItem
    -0.08
    çİĽä¸½
    -0.08
    ä¸ij
    -0.08
    çĨŁæĤī
    -0.08
    _compat
    -0.08
    _WORD
    -0.08
    Authorized
    -0.08
    POSITIVE LOGITS
    æľīèĩªå·±çļĦ
    0.13
    éĥ½æľīèĩªå·±
    0.12
    åĽºå®ļçļĦ
    0.11
    å°±æľīäºĨ
    0.11
    ç»°
    0.11
    身价
    0.10
    uchi
    0.10
    ä½ıæīĢ
    0.10
    æŀ¸
    0.10
    éħįå¤ĩ
    0.10
    Activations Density 0.181%

    No Known Activations