© 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. 34668
    Prev
    Next
    INDEX
    Explanations

    of/with/enzymes followed by protein/glu/H/tub/all

    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
    èµ°åĩºåİ»
    -0.10
    æİĤ
    -0.09
    .tie
    -0.08
    常年
    -0.08
    æ´±
    -0.08
    çģŃ
    -0.08
    çĩĭ
    -0.08
     Lair
    -0.08
     Lakes
    -0.08
    æĭĽèĤ¡
    -0.08
    POSITIVE LOGITS
    åļ
    0.09
    alse
    0.09
    åł¡åŀĴ
    0.09
    çľģæķĻèĤ²
    0.09
    ç¿©
    0.08
    æĸ°ä¸Ģ代
    0.08
    å¢ħ
    0.08
    urd
    0.08
    顾èĻij
    0.08
    ãģĹãģ¾
    0.08
    Activations Density 0.564%

    No Known Activations