© 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. 628
    Prev
    Next
    INDEX
    Explanations

    return to

    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
    éĩįéĩı
    -0.23
    足以
    -0.22
    enza
    -0.22
    åĬŁçĶ¨
    -0.22
    æī¿åĬŀ
    -0.21
    éĩįç»Ħ
    -0.21
    ä½ĵéĩı
    -0.21
    HING
    -0.21
    ç»ĪçĶŁ
    -0.20
     cái
    -0.20
    POSITIVE LOGITS
    ers
    0.25
    ìłĢ
    0.24
    Friendly
    0.23
    itty
    0.23
    aling
    0.23
    ABLE
    0.23
    als
    0.23
     welcome
    0.22
    edin
    0.21
    currently
    0.21
    Activations Density 0.001%

    No Known Activations