© 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. 10656
    Prev
    Next
    INDEX
    Explanations

    articles and reviews

    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
    era
    -0.10
    kat
    -0.09
    è¿Ļæľ¬ä¹¦
    -0.09
    sey
    -0.08
    ur
    -0.08
    ERA
    -0.08
    ложен
    -0.08
     Ur
    -0.07
    urry
    -0.07
    é½IJ
    -0.07
    POSITIVE LOGITS
    干货
    0.11
    快讯
    0.11
    çĭ¬å®¶
    0.11
    _unpack
    0.10
    .GetInstance
    0.10
    åį£
    0.10
    Exclusive
    0.10
    pong
    0.09
     ÙĨÙĤ
    0.09
    ainers
    0.09
    Activations Density 0.078%

    No Known Activations