© 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. 57616
    Prev
    Next
    INDEX
    Explanations

    Snoop or Snoopy,rell, ivas, appet

    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
    éĽī
    -0.10
    aters
    -0.10
    éªļ
    -0.10
    æŦ
    -0.10
    oup
    -0.10
    Pawn
    -0.09
    åĴ¨è¯¢æľįåĬ¡
    -0.09
    åĸīåĴĻ
    -0.09
    Penn
    -0.09
    å¤įå·¥
    -0.09
    POSITIVE LOGITS
     tyre
    0.09
     tire
    0.08
    é£Ļ
    0.08
    åģļçļĦäºĭæĥħ
    0.08
    å¤ĸçķĮ
    0.08
    иÑĢ
    0.08
    cale
    0.08
     Tire
    0.08
    亥
    0.07
    éĽį
    0.07
    Activations Density 0.001%

    No Known Activations