© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    front

    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
    osp
    -0.09
    å»¶æľŁ
    -0.09
    çĶ¨æīĭ
    -0.09
    å½ĵæĻļ
    -0.09
     Beet
    -0.08
    å¤ĸåĽ´
    -0.08
    æģĭ
    -0.08
    å®ŀéĻħæĥħåĨµ
    -0.08
    åľ¨åħ¶
    -0.08
    çĪ±å¥½èĢħ
    -0.08
    POSITIVE LOGITS
    -front
    0.13
    (front
    0.13
    /front
    0.12
    éĿ¢çĽ®
    0.11
    front
    0.11
     fronts
    0.10
     front
    0.10
    Front
    0.10
    äºĶå®ĺ
    0.09
    é»İæĺİ
    0.09
    Activations Density 0.132%

    No Known Activations