© 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. 58779
    Prev
    Next
    INDEX
    Explanations

    sparkling or glittering descriptions

    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
    æĦģ
    -0.10
    æŁĦ
    -0.10
    é£İæ³¢
    -0.09
     lore
    -0.09
    rost
    -0.09
    caff
    -0.08
    çģ«åĬĽ
    -0.08
     Weird
    -0.08
    ese
    -0.08
    Marks
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    éĹªçĥģ
    0.10
    æĻ¶
    0.10
    -eyed
    0.10
    pery
    0.09
    çIJĨäºĭä¼ļ
    0.09
    èĢĢçľ¼
    0.09
    BUF
    0.09
    ens
    0.08
    _auc
    0.08
    Activations Density 0.015%

    No Known Activations