© 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. 26714
    Prev
    Next
    INDEX
    Explanations

    untreated, not treated, not repaired

    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
    æĶ¶åıĸ
    -0.09
    åĩĨå¤ĩ好
    -0.09
    пон
    -0.09
    ä¸įæĺĵ
    -0.09
    çªģåıij
    -0.08
    åħ¼
    -0.08
    æºĸåĤĻ
    -0.08
     sandy
    -0.08
    é£ŀæī¬
    -0.08
    eor
    -0.08
    POSITIVE LOGITS
    å¦Ĥæŀľä¸į
    0.13
    æĭĸ延
    0.11
    éĶĻè¿ĩ
    0.11
    åıĬæŶ
    0.11
    延
    0.10
    èĶĵ延
    0.10
    骥
    0.10
    éķ¿æľŁ
    0.10
    延ç»Ń
    0.10
    uez
    0.10
    Activations Density 0.072%

    No Known Activations