© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    _section, questions, article, column

    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
     loos
    -0.25
     Reno
    -0.23
    ç¾ģ
    -0.23
    .eu
    -0.22
    -trained
    -0.22
    olec
    -0.22
    dao
    -0.21
    è°Ķ
    -0.21
     trainable
    -0.21
     League
    -0.21
    POSITIVE LOGITS
     therein
    0.37
     mention
    0.28
    æıIJåĪ°
    0.27
    çļĦä¸Ģ项
    0.25
    åħ¶ä¸Ń
    0.25
     specifically
    0.24
    祯
    0.24
    _section
    0.24
     amongst
    0.24
    -quote
    0.24
    Activations Density 0.391%

    No Known Activations