© 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. 1766
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    éĶŃ
    -0.09
    åIJĦ大
    -0.09
    èĶļ
    -0.09
    unsch
    -0.09
    efined
    -0.09
    诱人
    -0.09
    窨
    -0.09
    åľŁè±Ĩ
    -0.09
    æĬ½çĥŁ
    -0.08
    妲
    -0.08
    POSITIVE LOGITS
    éĽĨè£ħ
    0.08
    ä¸į让
    0.08
    edio
    0.08
    象
    0.08
    ç»ŀ
    0.08
    åĬªåĬĽ
    0.08
    HTTPRequest
    0.07
    imple
    0.07
    ads
    0.07
    LocalizedString
    0.07
    Activations Density 0.010%

    No Known Activations