© 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. 825
    Prev
    Next
    INDEX
    Explanations

    recovery and repair

    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
    æĶ¾çľ¼
    -0.29
    èĪĴéĢĤ
    -0.28
    æݨè¡Į
    -0.26
    åĬłéĩį
    -0.25
    æĬķ
    -0.23
    审ç¾İ
    -0.23
    /gin
    -0.23
    ç´§åĩij
    -0.23
     cruising
    -0.23
     recruits
    -0.22
    POSITIVE LOGITS
    æĮ½æķij
    0.44
    ä¿®å¤į
    0.42
    æĬ¢æķij
    0.39
    æĮ½åĽŀ
    0.38
    æī¾åĽŀ
    0.38
     recovery
    0.38
     recover
    0.37
    recover
    0.36
    æģ¢å¤į
    0.35
     salv
    0.34
    Activations Density 0.024%

    No Known Activations