© 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. 864
    Prev
    Next
    INDEX
    Explanations

    items found or taken

    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
    第ä¸Ģ家
    -0.26
    Ñģад
    -0.26
    apter
    -0.24
    åħīçݯ
    -0.23
    ville
    -0.23
    bout
    -0.23
    icken
    -0.23
     interviewed
    -0.22
     Savannah
    -0.22
    åŀĤ缴
    -0.22
    POSITIVE LOGITS
    éĴ¥åĮĻ
    0.31
     unlocked
    0.28
    _found
    0.27
     forbidden
    0.26
    åݨæĪ¿
    0.26
     borrowed
    0.26
     discarded
    0.25
    ä¸įå½ĵ
    0.25
    æĭ¿æĿ¥
    0.25
     found
    0.25
    Activations Density 0.047%

    No Known Activations