© 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. 48874
    Prev
    Next
    INDEX
    Explanations

    daughter of

    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
    åıijçĶŁçļĦ
    -0.09
    è¿Ļ件
    -0.09
     bis
    -0.09
    æĴº
    -0.09
    迺
    -0.09
    çĺ¿
    -0.09
    amina
    -0.08
    读åIJİ
    -0.08
    è¿Ļåıª
    -0.08
    åħ¨æł¡
    -0.08
    POSITIVE LOGITS
    hood
    0.11
     slump
    0.09
    кÑĢа
    0.09
    etimes
    0.09
    ÇĴ
    0.09
    媳å¦ĩ
    0.08
    ÙĦاÙĨ
    0.08
    orted
    0.08
    ntag
    0.08
    åŃ«
    0.08
    Activations Density 0.042%

    No Known Activations