© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    bell ringing and notifications

    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
    ä¸¤å¼ł
    -0.24
    orne
    -0.21
    èĬ¸
    -0.21
    èĻ¬
    -0.21
    æĶ¾æīĭ
    -0.21
    DVD
    -0.21
    HQ
    -0.20
    abilia
    -0.20
    äºĶå®ĺ
    -0.20
    ocha
    -0.20
    POSITIVE LOGITS
     bells
    0.45
    åĵįèµ·
    0.34
    ðŁĶĶ
    0.33
     ringing
    0.32
    éĵĥ
    0.31
    éĵĽ
    0.30
    声åĵį
    0.29
     bell
    0.29
     notification
    0.28
    åı®
    0.27
    Activations Density 0.027%

    No Known Activations