© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    numbers and STA

    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
    mium
    -0.23
    è²Ĥ
    -0.21
    Ĺı
    -0.21
    éľĸ
    -0.21
    .builders
    -0.21
    yaw
    -0.21
    æķĪæŀľåĽ¾
    -0.21
    夫å¦ĩ
    -0.21
    ilder
    -0.20
    ä½ĵåĪ¶
    -0.20
    POSITIVE LOGITS
    STA
    0.29
    sta
    0.27
    æĻ®
    0.25
    ç«ĭæ¡Ī
    0.25
     querying
    0.23
     STA
    0.23
     CLICK
    0.22
    oting
    0.22
     click
    0.22
     clicking
    0.21
    Activations Density 0.010%

    No Known Activations