© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    numbers followed by abbreviations or punctuation

    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
     objectively
    -0.24
     signings
    -0.23
    åī¯å¸Ĥéķ¿
    -0.22
     inputFile
    -0.21
    existent
    -0.21
    lei
    -0.21
     '\''
    -0.21
    å°ıåºĹ
    -0.21
     Gim
    -0.21
    naire
    -0.20
    POSITIVE LOGITS
    -of
    0.25
    ican
    0.24
    erm
    0.22
    æ²IJæµ´
    0.22
    crypt
    0.22
     persons
    0.22
    è¿ľç¨ĭ
    0.22
    âĹ»
    0.21
    rud
    0.21
    èĤļ
    0.21
    Activations Density 0.005%

    No Known Activations