© 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. 49376
    Prev
    Next
    INDEX
    Explanations

    Python package installation scripts

    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
    ç«ŀ
    -0.09
     ÙĦتØŃÙĤÙĬÙĤ
    -0.09
    lus
    -0.09
    vla
    -0.09
    _compat
    -0.08
    粪
    -0.08
    esen
    -0.08
     unab
    -0.08
    æĮŁ
    -0.08
     originals
    -0.08
    POSITIVE LOGITS
    ocol
    0.10
    berger
    0.09
    çĻ¾äº¿
    0.09
    _SKIP
    0.09
    åĢĴåľ¨
    0.08
    å¤Ł
    0.08
    ä¸į认è¯Ĩ
    0.08
     нед
    0.08
    åİĨ
    0.08
    é¹Ń
    0.08
    Activations Density 0.457%

    No Known Activations