© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1280
    Prev
    Next
    INDEX
    Explanations

    conditions are met

    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
    /from
    -0.26
     _______,
    -0.24
     respectively
    -0.24
    bas
    -0.24
    åı¦å¤ĸ
    -0.23
    ä½Ĩä¸įéĻIJäºİ
    -0.23
     pues
    -0.22
    æ¯Ķå¦Ĥ说
    -0.22
    ally
    -0.22
     sidelines
    -0.22
    POSITIVE LOGITS
     goal
    0.31
    ç»ĵæŀľæĺ¾ç¤º
    0.30
     result
    0.28
     aim
    0.27
     researchers
    0.26
    éĢĻäºĽ
    0.26
     resultado
    0.26
     implication
    0.25
    人ãģ¯
    0.24
     results
    0.24
    Activations Density 0.405%

    No Known Activations