© 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. 665
    Prev
    Next
    INDEX
    Explanations

    trout and salmon topics

    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
    éľĪ
    -0.23
    ysz
    -0.23
    ä¸Ģå¥Ĺ
    -0.21
     /*#__
    -0.21
    ials
    -0.21
    äºĨ大éĩıçļĦ
    -0.21
    æ²¹çĶ°
    -0.21
    éĹ³
    -0.21
    ament
    -0.20
    OrUpdate
    -0.20
    POSITIVE LOGITS
    .apple
    0.24
    /apple
    0.23
     surprises
    0.22
    é«ĺåİŁ
    0.22
    manship
    0.22
    lin
    0.21
    .googleapis
    0.21
    -at
    0.21
    MEDIA
    0.21
     Mountain
    0.21
    Activations Density 0.001%

    No Known Activations