© 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. 2965
    Prev
    Next
    INDEX
    Explanations

    competition and struggles

    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
    YLE
    -0.25
     incons
    -0.24
    +=(
    -0.23
    flate
    -0.23
    ç»Ļ人ä¸Ģç§į
    -0.22
    nost
    -0.21
     sqr
    -0.21
    çĸ®
    -0.21
    cal
    -0.21
     ÐŁÐ¾Ñĩем
    -0.21
    POSITIVE LOGITS
    formats
    0.22
    çĭİ
    0.22
     доÑģÑĤ
    0.21
    æ´Ĺ礼
    0.21
     pace
    0.21
    çĶ©
    0.21
     ain
    0.21
    _mask
    0.21
    Į¨
    0.20
    æĮ¯
    0.20
    Activations Density 0.007%

    No Known Activations