© 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. 759
    Prev
    Next
    INDEX
    Explanations

    declaration of record, bag, official, list

    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
    ../../../
    -0.23
    iliary
    -0.21
     behalf
    -0.21
    licity
    -0.21
    SELL
    -0.20
    ellig
    -0.20
    IZER
    -0.19
    plies
    -0.19
    ÌĢ
    -0.19
    å¤ł
    -0.19
    POSITIVE LOGITS
    æĻ°
    0.29
    ings
    0.20
    å·²ä¹ħçļĦ
    0.19
    istribution
    0.19
    him
    0.18
    zelf
    0.18
     bankruptcy
    0.18
    ä¸ĢåĪĩéĥ½æĺ¯
    0.18
    ä¸įæ¸ħ
    0.18
    ëłģ
    0.18
    Activations Density 0.029%

    No Known Activations