© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    There are

    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
    åĪ°è¿ĻéĩĮ
    -0.23
     behalf
    -0.22
     sendo
    -0.22
    读åIJİ
    -0.21
     extortion
    -0.21
    /documents
    -0.21
    ãģıãģł
    -0.21
    说åĪ°è¿ĻéĩĮ
    -0.21
    æīĢåľ¨åľ°
    -0.21
    ãģĤãģŁãĤĬ
    -0.21
    POSITIVE LOGITS
    许å¤ļ
    0.41
    诸å¤ļ
    0.40
     many
    0.40
    ä¸įå°ij
    0.38
    æĹłæķ°
    0.36
    å¾Īå¤ļ
    0.35
    åĩłç§į
    0.35
     ways
    0.35
    許å¤ļ
    0.34
     MANY
    0.33
    Activations Density 0.115%

    No Known Activations