© 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. 1165
    Prev
    Next
    INDEX
    Explanations

    results-oriented

    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
    itional
    -0.24
    isci
    -0.22
    次è¦ģ
    -0.21
     Tale
    -0.20
    /she
    -0.20
    thing
    -0.20
    ä¸ĢåĽŀäºĭ
    -0.20
    uous
    -0.19
     respective
    -0.19
     ÐŁÐ¾Ñĩем
    -0.19
    POSITIVE LOGITS
    丰ç¡ķ
    0.35
    -oriented
    0.31
    æĪIJæķĪ
    0.28
    ä¸įä½³
    0.27
    /effects
    0.27
    /result
    0.26
    /results
    0.26
    /output
    0.25
    为导åIJij
    0.24
    oriented
    0.23
    Activations Density 0.066%

    No Known Activations