© 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. 18062
    Prev
    Next
    INDEX
    Explanations

    high school

    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
    REW
    -0.10
    çĶ¨å·¥
    -0.09
    ä¼ı
    -0.09
    çĮ·
    -0.09
    åĺİ
    -0.08
    ifu
    -0.08
    大å¹ħ
    -0.08
    ilden
    -0.08
    .RemoveAll
    -0.08
     pallet
    -0.08
    POSITIVE LOGITS
    éĺ´éĺ³
    0.10
    æľ
    0.09
    yard
    0.08
    宫
    0.08
    eor
    0.08
    PropertyValue
    0.08
    ask
    0.08
     pride
    0.08
    æĭ³å¤´
    0.08
    èĴĻ
    0.08
    Activations Density 0.086%

    No Known Activations