© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    time stamps am pm

    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
     ÑģÑĤÑĢем
    -0.23
    kre
    -0.23
    olver
    -0.22
    alette
    -0.21
    æݨåĭķ
    -0.21
    INDER
    -0.21
    irement
    -0.21
    oubles
    -0.21
    еÑĢÑĮ
    -0.21
    ewith
    -0.21
    POSITIVE LOGITS
    âĶ
    0.28
     rue
    0.28
     пÑĢоÑģ
    0.27
    ÎĴ
    0.26
     AM
    0.26
     (?)
    0.24
     Yours
    0.24
    âĹĦ
    0.24
     thumbs
    0.23
     Posting
    0.23
    Activations Density 0.039%

    No Known Activations