© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    spending and expenditure

    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
    çĦ¶æĺ¯
    -0.10
    ãĤĴè¿İ
    -0.09
    å´İ
    -0.09
    uish
    -0.09
    åľ¨ä¸Ĭæµ·
    -0.09
    rb
    -0.08
    åīįåı°
    -0.08
    atte
    -0.08
    åīįåIJİ
    -0.08
    åıijè¨Ģ人
    -0.08
    POSITIVE LOGITS
    æ°ı
    0.10
    arov
    0.10
    olini
    0.09
    éĺŁåıĭ
    0.09
    ergy
    0.09
    ylvania
    0.09
    aney
    0.09
    .writeln
    0.08
    ä¾
    0.08
    onium
    0.08
    Activations Density 0.007%

    No Known Activations