© 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. 37395
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    ä¼ļå½±åĵį
    -0.09
    èĥļ
    -0.09
    FormatException
    -0.08
    æĸ°ä¸ŃåĽ½
    -0.08
     Magick
    -0.08
    WF
    -0.08
    åĸľæ¬¢åIJĥ
    -0.08
    éĶ¤
    -0.08
    ä¸Ģå¤ľ
    -0.08
    åłĨ
    -0.08
    POSITIVE LOGITS
    æ¿ĢåĬ¨
    0.09
    ustin
    0.09
    vang
    0.08
    _HS
    0.08
    DTV
    0.08
    对èĩªå·±
    0.08
    湯
    0.08
    _BACKEND
    0.08
    itive
    0.08
     bay
    0.08
    Activations Density 0.024%

    No Known Activations