© 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. 57817
    Prev
    Next
    INDEX
    Explanations

    according to someone

    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
    éĢĤ度
    -0.09
    åĵī
    -0.09
    æŁĶ
    -0.09
    é«ĺä»·
    -0.09
    eral
    -0.09
    -divider
    -0.09
    çĮľ
    -0.08
    å®ŀåľ¨
    -0.08
    _DRV
    -0.08
    大å§IJ
    -0.08
    POSITIVE LOGITS
    åľ¨è¿Ļç§į
    0.11
    addtogroup
    0.10
    oste
    0.10
    olen
    0.10
    ëĿ¼ë©´
    0.10
    å²Ĥ
    0.10
    è¿Ļå¥Ĺ
    0.09
    åĽ½æľīèµĦ产
    0.09
    å·Ŀ
    0.09
    è¿Ļç§įæĸ¹æ³ķ
    0.09
    Activations Density 0.075%

    No Known Activations