© 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. 32351
    Prev
    Next
    INDEX
    Explanations

    sale and purchase of property

    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
    深交
    -0.10
    ç®ĢåİĨ
    -0.09
    æķ¬ä¸ļ
    -0.09
    å±Ĥ次
    -0.09
     Circ
    -0.09
    éĺħåİĨ
    -0.09
    .ny
    -0.09
    oftware
    -0.08
    è¿ĺç®Ĺ
    -0.08
    _drv
    -0.08
    POSITIVE LOGITS
    åĬŀåѦ
    0.11
    è¿ĻåĿĹ
    0.10
    ä¸ĢåĿĹ
    0.10
    æĴĤ
    0.09
    åĿļ
    0.09
    åľŁåľ°
    0.09
    ç½®æį¢
    0.09
    çĻ¾å¹´
    0.09
     land
    0.09
    éĤ»
    0.09
    Activations Density 0.206%

    No Known Activations