© 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. 6578
    Prev
    Next
    INDEX
    Explanations

    neckwear or accessories

    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
    uce
    -0.10
    aging
    -0.09
    æ´»çĿĢ
    -0.08
     totaled
    -0.08
    媳å¦ĩ
    -0.08
    orce
    -0.08
    èĩªé©¾
    -0.08
     sandals
    -0.08
     curb
    -0.08
    ç«ĻçĿĢ
    -0.08
    POSITIVE LOGITS
    è¡«
    0.11
    罩
    0.09
     Provid
    0.09
    ç¦ģ
    0.09
    alia
    0.09
    _stuff
    0.09
     stuff
    0.08
    æģ¤
    0.08
    丼
    0.08
     prze
    0.08
    Activations Density 0.016%

    No Known Activations