© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3058
    Prev
    Next
    INDEX
    Explanations

    numbers containing 8

    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
     fright
    -0.23
     terse
    -0.22
    spell
    -0.21
    WithDuration
    -0.20
     hur
    -0.20
    /dis
    -0.20
    CCI
    -0.20
    ILLS
    -0.20
    ÅĤow
    -0.20
     chiếu
    -0.20
    POSITIVE LOGITS
    æĥħ
    0.22
    çŃī缸åħ³
    0.22
    åķĨåĬ¡
    0.21
    çİĭåħĪçĶŁ
    0.21
    æ°´æ³¥
    0.21
    åħ¨åĽ½
    0.21
    å·¥ä½ľæĬ¥åijĬ
    0.20
    åĬŀ好
    0.20
    éĥģ
    0.20
    tors
    0.20
    Activations Density 0.002%

    No Known Activations