© 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. 973
    Prev
    Next
    INDEX
    Explanations

    technical forums and articles

    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
    åħ¥åĽŃ
    -0.26
    ohana
    -0.25
    仪表
    -0.24
    殿ä¸ĭ
    -0.23
     glass
    -0.23
    click
    -0.23
     click
    -0.23
    abee
    -0.23
    ypress
    -0.23
    çİ»çĴĥ
    -0.23
    POSITIVE LOGITS
    libc
    0.27
     ASCII
    0.27
     libc
    0.25
    åĪĨåĮº
    0.24
    éģį
    0.24
     Porn
    0.24
    è¿IJåĬ¿
    0.23
    .ascii
    0.23
    åĪĨå¸ĥ
    0.23
    abyte
    0.23
    Activations Density 0.024%

    No Known Activations