© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    tax returns and payments

    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
    çĺ¦
    -0.09
    éĻªåIJĮ
    -0.08
     Zam
    -0.08
    .cod
    -0.08
     ÑĨен
    -0.08
     thinly
    -0.08
    unu
    -0.08
    éĽĨè£ħ
    -0.08
    éĻªçĿĢ
    -0.08
    èŀį为ä¸Ģä½ĵ
    -0.08
    POSITIVE LOGITS
     tax
    0.19
    ç¨İæĶ¶
    0.19
     taxes
    0.19
    ç¨İåĬ¡
    0.18
    ç¨İ
    0.17
    纳ç¨İ
    0.17
     Tax
    0.16
    ç¨ħ
    0.16
    tax
    0.16
    -tax
    0.16
    Activations Density 0.118%

    No Known Activations