© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 429
    Prev
    Next
    INDEX
    Explanations

    below 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
    ann
    -0.26
    æĶ¾å¤§
    -0.24
     cottage
    -0.23
    itto
    -0.23
    è¿Ļ家ä¼Ļ
    -0.23
    ä¿ĺ
    -0.22
    åij¨
    -0.22
    ")+
    -0.22
    çĶ°
    -0.21
    anny
    -0.21
    POSITIVE LOGITS
    عب
    0.22
    éģĤ
    0.22
    æĽ´å¼º
    0.22
    zion
    0.22
    çļĦèĦļæŃ¥
    0.21
    _assert
    0.21
    ç»ıæŁ¥
    0.21
    ereg
    0.20
    .Batch
    0.20
    Checked
    0.20
    Activations Density 0.002%

    No Known Activations