© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53173
    Prev
    Next
    INDEX
    Explanations

    telecommunications closet or equipment rack

    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
    è£ģ
    -0.10
    çĩŁ
    -0.10
    èIJ¥
    -0.10
    å°ķ
    -0.09
    reen
    -0.09
    å½»
    -0.09
    afi
    -0.09
    istle
    -0.09
    _CFG
    -0.09
    èIJ¥ä¸ļ
    -0.08
    POSITIVE LOGITS
    ç®±åŃIJ
    0.12
     closet
    0.11
    BOX
    0.10
     closets
    0.09
    ä¼ı
    0.09
     Bowman
    0.09
    ettel
    0.09
    ithe
    0.09
     BOX
    0.09
     ÑĥпÑĢавлениÑı
    0.08
    Activations Density 0.137%

    No Known Activations