© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36354
    Prev
    Next
    INDEX
    Explanations

    fund spending, discretionary income, incremental financing

    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
    .au
    -0.09
    à¸Ĭา
    -0.08
    idor
    -0.08
     ram
    -0.08
    лик
    -0.08
     Wake
    -0.08
    ram
    -0.07
    oro
    -0.07
    类似çļĦ
    -0.07
    æĦıè¯ĨåĪ°
    -0.07
    POSITIVE LOGITS
    Ñģка
    0.10
    æ´µ
    0.10
    ä¸Ģ个èģĮä¸ļ
    0.10
    lse
    0.09
     лиÑĩно
    0.09
    åĴĮ个人
    0.09
    oftware
    0.09
    çĭ¬åħ·
    0.09
    æĪIJçĨŁ
    0.09
    大è¡Ĺ
    0.09
    Activations Density 0.015%

    No Known Activations