© 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. 35216
    Prev
    Next
    INDEX
    Explanations

    ombudsman or officer titles

    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
    æħ·
    -0.11
    éĹªçĥģ
    -0.09
    ä¾ł
    -0.09
    绸
    -0.09
    åĩºåħ¥
    -0.09
    _IMPORTED
    -0.09
    adro
    -0.09
    eward
    -0.09
    istringstream
    -0.09
    仪表
    -0.09
    POSITIVE LOGITS
    举æĬ¥
    0.09
    éĢĶå¾Ħ
    0.09
    æľºåĪ¶
    0.09
    ä¸įçķĻ
    0.09
    çļĦçIJĨ念
    0.08
    çĥŁèįī
    0.08
    æĢ¨
    0.08
    isoner
    0.08
    dere
    0.08
    onic
    0.08
    Activations Density 0.017%

    No Known Activations