© 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. 1914
    Prev
    Next
    INDEX
    Explanations

    centrifugal or tweet

    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
    æĻ¦
    -0.25
    zar
    -0.23
    URED
    -0.22
    èĤĨ
    -0.22
    WER
    -0.22
    uring
    -0.21
    ÑĤив
    -0.20
    wer
    -0.20
    对ä¼ģä¸ļ
    -0.20
    代
    -0.20
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.24
    ä¸İåIJ¦
    0.23
    able
    0.23
     halls
    0.22
    Opens
    0.22
    çĽį
    0.22
    worthy
    0.21
    责任ç¼ĸè¾ij
    0.21
    ularity
    0.21
    ability
    0.21
    Activations Density 0.004%

    No Known Activations