© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    now available

    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
     aver
    -0.25
    ecessarily
    -0.24
     Haram
    -0.24
     necessarily
    -0.23
    å±Ĥå±Ĥ
    -0.23
    è¯ĦåĪ¤
    -0.23
    idences
    -0.23
    ringe
    -0.23
    éļħ
    -0.23
     kInstruction
    -0.22
    POSITIVE LOGITS
    æĸ°çīĪ
    0.42
    æĸ°çļĦ
    0.41
    æĸ°ãģŁ
    0.37
    åħ¨æĸ°çļĦ
    0.36
     new
    0.35
    æĽ´æĸ°
    0.35
    ä¸Ģ个æĸ°çļĦ
    0.34
    åħ¨æĸ°
    0.34
    æĸ°ãģĹãģĦ
    0.34
     revamped
    0.34
    Activations Density 0.073%

    No Known Activations