© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    Tax act legislation

    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
     vice
    -0.25
    alom
    -0.24
    entials
    -0.23
    ä¸ĩåħĥ以ä¸Ĭ
    -0.23
    ä¸ĭçıŃ
    -0.23
    å³Ĵ
    -0.23
    å½Ĵå±ŀ
    -0.23
    éĤĤ
    -0.23
    _dash
    -0.23
    翼
    -0.23
    POSITIVE LOGITS
    åıĸ代
    0.32
    åij¨æľŁ
    0.28
     Act
    0.27
    æijĴ
    0.26
     cycle
    0.25
    .createQuery
    0.24
     Implementation
    0.24
    poster
    0.24
    åĪ¶åº¦
    0.23
    æ³ķæ¡Ī
    0.23
    Activations Density 0.049%

    No Known Activations