© 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. 701
    Prev
    Next
    INDEX
    Explanations

    section, article, Annex, §

    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
    å¤įä»ĩ
    -0.26
    pty
    -0.23
    hec
    -0.22
    Mgr
    -0.22
    _mgr
    -0.22
    åĩĨå¤ĩå·¥ä½ľ
    -0.22
    peon
    -0.21
    TRACE
    -0.21
    _HOT
    -0.21
    éĢ¾
    -0.21
    POSITIVE LOGITS
    æĺİç¡®è§Ħå®ļ
    0.26
    è§Ħå®ļ
    0.26
     laws
    0.25
    鸯
    0.24
     Defines
    0.24
    ðŁijį
    0.23
    é£İçŃĿ
    0.23
    é¦IJ
    0.23
     &
    0.23
    &p
    0.23
    Activations Density 0.051%

    No Known Activations