© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    extremely common

    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
    ivr
    -0.24
     ero
    -0.23
    asti
    -0.22
    ç¡®å®ŀ
    -0.22
     tj
    -0.22
    æĺ¾çĦ¶
    -0.22
    _UD
    -0.22
    l
    -0.21
    URN
    -0.21
    ä¾ĭè¡Į
    -0.21
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.25
     lite
    0.24
    æĬī
    0.23
    çĽ¸å¯¹æĿ¥è¯´
    0.23
     DESC
    0.22
    /co
    0.22
    lessly
    0.22
    ãģ§ãģ¯ãģĤãĤĬãģ¾ãģĽãĤĵ
    0.22
    ãĤıãģijãģ§ãģ¯ãģªãģĦ
    0.22
     compared
    0.21
    Activations Density 0.585%

    No Known Activations