© 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. 2265
    Prev
    Next
    INDEX
    Explanations

    already

    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
     prot
    -0.27
     Rosen
    -0.24
    prot
    -0.24
    ä¸Ģ对
    -0.23
     concept
    -0.23
    ç»Ĥ
    -0.22
    ä¸įå½±åĵį
    -0.22
    æ¦Ĥ念
    -0.22
    romo
    -0.22
     unm
    -0.22
    POSITIVE LOGITS
    好ä¸į容æĺĵ
    0.50
     already
    0.41
     fragile
    0.40
    æľ¬æĿ¥å°±
    0.39
    å·²ç»ı被
    0.38
     Already
    0.38
    already
    0.36
    Already
    0.36
    _already
    0.35
    èĦĨå¼±
    0.33
    Activations Density 0.094%

    No Known Activations