© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    as far as possible

    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´Ľèµ·
    -0.24
    æĢ»æĶ¶åħ¥
    -0.22
    åĨ¢
    -0.21
     swe
    -0.21
    åĶ®ç¥¨
    -0.21
    submission
    -0.20
    -Version
    -0.20
    regist
    -0.20
    izin
    -0.20
    èĮĥåĨ°
    -0.20
    POSITIVE LOGITS
    æĪij
    0.25
    æľ¬ç½ijç«Ļ
    0.25
    çŁ¥
    0.25
     име
    0.24
     provided
    0.24
    æĪijå½ĵæŶ
    0.24
     know
    0.23
    ãn
    0.23
     circumstances
    0.23
    çŁ¥æĻĵ
    0.23
    Activations Density 0.009%

    No Known Activations