© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    without limitation

    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
    ç»Īæŀģ
    -0.28
    bil
    -0.23
    antic
    -0.22
    æį¢æĿ¥
    -0.22
    ä¸ĭä¸ĢæŃ¥
    -0.21
    úc
    -0.21
    percent
    -0.21
    缸继
    -0.21
     ratios
    -0.21
    å¾ħ
    -0.21
    POSITIVE LOGITS
    edly
    0.32
    иÑĤелÑĮ
    0.24
     whatsoever
    0.24
     NYPD
    0.23
    ivist
    0.22
    .issue
    0.22
    äºİæѤ
    0.21
     Epstein
    0.21
    æĪĸå¤ļ
    0.21
    ìĺ¥
    0.21
    Activations Density 0.006%

    No Known Activations