© 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. 34236
    Prev
    Next
    INDEX
    Explanations

    see if

    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
    棣
    -0.09
    awesome
    -0.09
    éĩijèī²
    -0.09
    .present
    -0.08
    uer
    -0.08
     Leisure
    -0.08
    绵
    -0.08
    sel
    -0.08
    ilig
    -0.08
    çľĭèµ·æĿ¥
    -0.08
    POSITIVE LOGITS
    æľīå¤ļå°ij
    0.12
    æĺ¯åIJ¦æľī
    0.11
     whether
    0.10
    æĺ¯åIJ¦
    0.10
    æľī没æľī
    0.09
    å¥ij约
    0.09
    åīįæīĢ
    0.09
    京åī§
    0.09
    parable
    0.09
    纹
    0.09
    Activations Density 0.052%

    No Known Activations