© 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. 39272
    Prev
    Next
    INDEX
    Explanations

    owner, renter, or slave

    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
    åİ»çľĭçľĭ
    -0.10
    uity
    -0.10
    éĢģåİ»
    -0.09
    ä¸ĩè¾¾
    -0.09
    æĤ²åĵĢ
    -0.09
    纤
    -0.09
    pend
    -0.09
    èĬ
    -0.08
    ç»Ĵ
    -0.08
    çĽĺæ´»
    -0.08
    POSITIVE LOGITS
    kest
    0.10
    kea
    0.09
    ç½®ä¸ļ
    0.09
    å¹´éĻIJ
    0.09
    angen
    0.09
    æľĢåIJİä¸Ģ次
    0.09
    UTH
    0.09
    ä¸įåħ·å¤ĩ
    0.09
    éĻIJ
    0.09
    _DISABLED
    0.08
    Activations Density 0.098%

    No Known Activations