© 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. 670
    Prev
    Next
    INDEX
    Explanations

    fractions, ratios, or proportions

    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
     initials
    -0.26
    ehler
    -0.23
    éĺ²èħIJ
    -0.23
     barg
    -0.23
     tim
    -0.22
    æģĤ
    -0.22
     fil
    -0.22
    åįłæį®äºĨ
    -0.22
     Gram
    -0.21
     wit
    -0.21
    POSITIVE LOGITS
    éĻª
    0.29
    oser
    0.23
    million
    0.23
    æŃ£å¸¸ä½¿çĶ¨
    0.22
     Wool
    0.22
    ippy
    0.22
    eling
    0.22
    许åı¯
    0.21
    æ¯ĶåĪĨ
    0.21
    åħ³ç³»
    0.21
    Activations Density 0.073%

    No Known Activations