© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    currency symbols and numbers

    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
    ä¸İåıijå±ķ
    -0.24
     NHS
    -0.24
    åħħå®ŀ
    -0.23
    rä
    -0.23
    主è§Ĥ
    -0.22
    ÑģÑĤÑĢой
    -0.22
    ermen
    -0.21
     CHUNK
    -0.21
    å³ģ
    -0.21
    xfff
    -0.20
    POSITIVE LOGITS
    /
    0.32
    çķĻåѦçĶŁ
    0.28
     Translate
    0.28
    Translate
    0.28
    å¤ĸæ±ĩ
    0.27
    å¤ĸç±į
    0.27
    æĪĸ
    0.27
    /mac
    0.26
    æµ·å¤ĸ
    0.26
    ترجÙħ
    0.26
    Activations Density 0.031%

    No Known Activations