© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 84
    Prev
    Next
    INDEX
    Explanations

    deductions, withholding, deduct, subtract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è§Ħ模æľĢ大
    -0.25
    chter
    -0.24
    çī¡
    -0.24
     Ring
    -0.23
    æ·¹
    -0.23
    èī¯å¥½
    -0.22
     Foo
    -0.22
    imore
    -0.21
    çIJ¥
    -0.21
    uchen
    -0.21
    POSITIVE LOGITS
    æī£
    0.34
     deductions
    0.33
    æİī
    0.31
     subtract
    0.30
    åĩı
    0.30
     deducted
    0.29
     deduct
    0.27
    æ¸Ľ
    0.26
     savings
    0.26
    åĩıå°ijäºĨ
    0.25
    Activations Density 0.025%

    No Known Activations