© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35804
    Prev
    Next
    INDEX
    Explanations

    excipients, films, methods

    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
    æķĪåĬĽ
    -0.10
    ä¿Ŀåģ¥
    -0.10
    lint
    -0.08
    çķĻåŃĺ
    -0.08
    ullah
    -0.08
    ä¿ļ
    -0.08
    æĹłè®ºå¦Ĥä½ķ
    -0.08
    å¸Ĥåľºä¸Ĭ
    -0.08
    åĦ¿
    -0.08
    HE
    -0.08
    POSITIVE LOGITS
    ãģ«å¯
    0.09
    GetWidth
    0.09
    ä¸Ģåı°
    0.09
     Caf
    0.09
    .FileNotFoundException
    0.08
    Õ±
    0.08
    éħįæľī
    0.08
    getMethod
    0.08
    ÑģÑĤеÑĢ
    0.08
    .getMethod
    0.08
    Activations Density 0.026%

    No Known Activations