© 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. 1868
    Prev
    Next
    INDEX
    Explanations

    development networks serviceName

    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
     seals
    -0.23
    æ¿ij
    -0.23
    ä¸ĭè¾¾
    -0.23
    æİĸ
    -0.22
    éķĩæ±Ł
    -0.22
    .Anchor
    -0.22
    mpeg
    -0.22
    ={({
    -0.21
     patio
    -0.21
    ROME
    -0.21
    POSITIVE LOGITS
    æİ°
    0.26
    ħ§
    0.25
    _blend
    0.23
    æĹ¶æľŁ
    0.23
    åļ¼
    0.22
     serviceName
    0.22
     Whole
    0.22
    istic
    0.22
    ragment
    0.22
    æľŁ
    0.22
    Activations Density 0.001%

    No Known Activations