© 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. 1826
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    oret
    -0.28
    éģĨ
    -0.22
    åĽłä¸ºå¥¹
    -0.21
    åħ¨çº¿
    -0.20
    åĽłä¸ºä»ĸ
    -0.20
    äºİæĺ¯
    -0.20
    omm
    -0.19
    èĮĥåĨ°
    -0.19
    orem
    -0.19
    erce
    -0.19
    POSITIVE LOGITS
    /how
    0.42
    soever
    0.39
     else
    0.34
     happens
    0.34
    else
    0.33
    æł·çļĦ
    0.32
     happened
    0.31
    Else
    0.29
     kind
    0.27
    wg
    0.26
    Activations Density 0.134%

    No Known Activations