© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    respondent / appellee lawyer

    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
    ked
    -0.24
    åĴ¥
    -0.21
     surplus
    -0.21
     vez
    -0.20
    å°ģéĿ¢
    -0.20
    ÑĮев
    -0.20
     Needed
    -0.20
     Went
    -0.20
    orra
    -0.20
    æ°ijå¿ĥ
    -0.20
    POSITIVE LOGITS
    亦
    0.25
    åĨ²
    0.23
    Disclosure
    0.23
    æīĢè¿°
    0.23
    IMA
    0.23
    稻
    0.22
    óż
    0.22
    shadow
    0.22
    åijĽ
    0.22
    ä¿¡æģ¯æĬ«éľ²
    0.22
    Activations Density 0.074%

    No Known Activations