© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    time remaining or ending

    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
    ynos
    -0.25
    æĹ¶å¸¸
    -0.22
    æ·±å¤Ħ
    -0.22
    ONSE
    -0.21
     familiar
    -0.21
    è½Ń
    -0.21
    ä¸įåIJĮç¨ĭ度
    -0.21
     truth
    -0.21
    itech
    -0.21
    edb
    -0.21
    POSITIVE LOGITS
    ä¸Ģåı¥
    0.28
    éĴŁ
    0.28
    éIJĺ
    0.27
    aky
    0.25
    åĩºå¢ĥ
    0.25
    -pocket
    0.24
    ties
    0.23
    è¢ľ
    0.23
     flirting
    0.22
     Pocket
    0.22
    Activations Density 0.004%

    No Known Activations