© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation or days

    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
    çIJļ
    -0.23
     mur
    -0.23
    è¾¾æĪIJ
    -0.23
    æ¶Ī
    -0.22
    Reach
    -0.22
    è¾¾æłĩ
    -0.21
    erÃł
    -0.20
    è¾Ĥ
    -0.20
     bú
    -0.20
    ToStr
    -0.20
    POSITIVE LOGITS
     AUTHORS
    0.23
    é¡·
    0.22
     vign
    0.21
     quien
    0.21
    ç¬
    0.21
    _PD
    0.20
    -scripts
    0.20
    æĤłä¹ħ
    0.20
    ancial
    0.20
    istra
    0.20
    Activations Density 0.043%

    No Known Activations