© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    to destination

    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
    èĩªæĿ¥
    -0.10
    umerator
    -0.10
    alez
    -0.10
    zech
    -0.10
    æĻļæĬ¥
    -0.09
    åĩºè·¯
    -0.09
    宥
    -0.09
    çĴĭ
    -0.09
    thetic
    -0.09
    æĶ¶åĽŀ
    -0.09
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.11
     indem
    0.09
    ity
    0.09
    datable
    0.09
    京津
    0.08
     serialVersionUID
    0.08
    neath
    0.08
    redit
    0.07
     noqa
    0.07
    ió
    0.07
    Activations Density 0.018%

    No Known Activations