© 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. 22697
    Prev
    Next
    INDEX
    Explanations

    phone numbers and codes

    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
    umbs
    -0.08
    å»Ĭ
    -0.08
    宾客
    -0.08
    æݨ
    -0.08
    éħ±
    -0.08
    åĴ§
    -0.08
    æĿª
    -0.08
    äºĮç»´çłģ
    -0.07
    ä¸ĬåįĬå¹´
    -0.07
     Liber
    -0.07
    POSITIVE LOGITS
    åĤ²
    0.11
    _ioctl
    0.09
     eBook
    0.09
    å°±è§īå¾Ĺ
    0.09
    .callbacks
    0.09
    à¹Ĥà¸ģ
    0.09
    åĸĦäºİ
    0.08
    æĵħéķ¿
    0.08
    é«ĺéĢŁåıijå±ķ
    0.08
    GLOBALS
    0.08
    Activations Density 0.174%

    No Known Activations