© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    kinetic and kinetoplastida

    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
    edException
    -0.11
    é¾Ħ
    -0.10
    ä¸Ģå¥Ĺ
    -0.09
    æĻĹ
    -0.09
    åıĮçľ¼
    -0.08
    croft
    -0.08
    æĺĬ
    -0.08
    аÑħ
    -0.08
    è·¯æ¼Ķ
    -0.08
    iants
    -0.08
    POSITIVE LOGITS
    etic
    0.10
    ilty
    0.10
    ematic
    0.10
    etically
    0.10
    ematics
    0.09
    ema
    0.09
    ney
    0.09
    folk
    0.09
    esthetic
    0.09
     dáng
    0.09
    Activations Density 0.062%

    No Known Activations