© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8821
    Prev
    Next
    INDEX
    Explanations

    carrying case, container, box

    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
    æĸ·
    -0.10
    æĸŃ
    -0.10
     Knife
    -0.09
    .stamp
    -0.09
    _SM
    -0.08
    èIJ¥
    -0.08
    Crow
    -0.08
    _segment
    -0.08
    Segment
    -0.08
    çĤ¹èµŀ
    -0.08
    POSITIVE LOGITS
    ç®±
    0.13
    容åĻ¨
    0.12
     container
    0.12
     box
    0.11
     BOX
    0.11
     boxes
    0.11
    çĽĴåŃIJ
    0.11
    ç®±åŃIJ
    0.10
     containers
    0.10
    棺
    0.10
    Activations Density 0.087%

    No Known Activations