© 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. 39196
    Prev
    Next
    INDEX
    Explanations

    calming or therapeutic effects

    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
    çĶ¨é¤IJ
    -0.10
    èĬĤ约
    -0.09
    èĬĤçľģ
    -0.09
    åIJĥäºı
    -0.09
    Spr
    -0.08
    ä¸įç»ı
    -0.08
    é£İè²Į
    -0.08
    çIJ³
    -0.08
    åł¡
    -0.08
    çĶŁãģ¾ãĤĮ
    -0.08
    POSITIVE LOGITS
    æħ°
    0.12
    麻çĹ¹
    0.11
    çĸĹ
    0.11
    å¢ĥ
    0.09
    immers
    0.09
     bibli
    0.09
    æĭŁ
    0.09
    çģ¸
    0.09
    åı¯ä»¥å¸®åĬ©
    0.08
    éĢĥ离
    0.08
    Activations Density 0.091%

    No Known Activations