© 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. 28049
    Prev
    Next
    INDEX
    Explanations

    send something

    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
    åħ¨æĹ¥
    -0.13
    骨干
    -0.09
    éģįåıĬ
    -0.08
    çıĢ
    -0.08
    æĸ°åĬł
    -0.08
    åİļ度
    -0.08
    纵深
    -0.08
    é¼ĵ
    -0.08
    éģįå¸ĥ
    -0.08
    æĤ¬å¿µ
    -0.08
    POSITIVE LOGITS
    .sz
    0.10
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    .UR
    0.09
     Deliver
    0.09
    озв
    0.08
    .foundation
    0.08
    _PRI
    0.08
    idel
    0.08
    ãĥĬãĥ«
    0.08
    .PLAIN
    0.08
    Activations Density 0.007%

    No Known Activations