© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    results from calculations

    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
    åĽłä¸ºå®ĥ
    -0.24
     главное
    -0.24
    oyer
    -0.23
    ble
    -0.22
    ä¸İåħ¶ä»ĸ
    -0.22
    æĽ´éĩįè¦ģçļĦ
    -0.22
    çĪ±äºº
    -0.22
    inea
    -0.22
    zar
    -0.21
     gratuit
    -0.21
    POSITIVE LOGITS
    å¾Ĺåĩº
    0.40
     resulting
    0.38
    çļĦç»ĵæŀľ
    0.37
    yield
    0.36
    çµIJæŀľ
    0.34
    ç»ĵæŀľ
    0.34
     yielding
    0.34
     yields
    0.33
     yield
    0.32
    å¾ĹåĪ°
    0.32
    Activations Density 0.197%

    No Known Activations