© 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. 53578
    Prev
    Next
    INDEX
    Explanations

    fees, taxes, dues, or premiums

    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
    éĢĨ转
    -0.10
    çģ¾åĮº
    -0.09
    åħ»æĪIJ
    -0.09
    гаÑĢ
    -0.09
    èĢIJ
    -0.09
    éĩįçĤ¹é¡¹çĽ®
    -0.09
    äºĮ线
    -0.08
    èĤłèĥĥ
    -0.08
    çķĻè¨ĢæĿ¿
    -0.08
    已达
    -0.08
    POSITIVE LOGITS
    缴纳
    0.15
    ç¼´è´¹
    0.15
    åŃ¦è´¹
    0.14
     fee
    0.14
    æĶ¶è´¹
    0.14
     fees
    0.14
    æĶ¶åıĸ
    0.12
    fee
    0.12
    ç¼´
    0.12
    ç¹³
    0.12
    Activations Density 0.239%

    No Known Activations