© 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. 49994
    Prev
    Next
    INDEX
    Explanations

    decreasing or falling

    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
     foss
    -0.09
    ган
    -0.09
    æŃ¤ä¸¾
    -0.09
     dess
    -0.09
     капиÑĤал
    -0.09
    abby
    -0.09
    å«
    -0.08
    çĥĤ
    -0.08
    çĦĻ
    -0.08
    REE
    -0.08
    POSITIVE LOGITS
    areth
    0.10
    åħ¨å¤©
    0.09
    ä¸Ģç¬ij
    0.09
    _rq
    0.08
    åľ¨æĦı
    0.08
    èĪ¶
    0.08
    æŁ¥çľĭæĽ´å¤ļ
    0.08
    å°ıéķĩ
    0.08
    天使
    0.08
    设æĸ½å»ºè®¾
    0.08
    Activations Density 0.009%

    No Known Activations