© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    preceding place names

    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
    acd
    -0.23
     plague
    -0.22
    èĢģ人家
    -0.21
     Frankie
    -0.21
    èĭĮ
    -0.21
    æģ¶
    -0.21
    è·¯éĿ¢
    -0.21
    otent
    -0.20
    oland
    -0.20
    ä¸ºä½ł
    -0.20
    POSITIVE LOGITS
    Aux
    0.26
    ardin
    0.24
    aic
    0.23
    综
    0.23
    è¾ħåĬ©
    0.22
     Auxiliary
    0.22
     Aux
    0.22
    ensible
    0.22
    æĿĤ
    0.22
    aina
    0.22
    Activations Density 0.465%

    No Known Activations