© 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. 596
    Prev
    Next
    INDEX
    Explanations

    risk or lack of

    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
    ITO
    -0.24
    ena
    -0.23
    discover
    -0.22
    ↵     ↵
    -0.22
    Variable
    -0.21
    å¿ĥèĦıçĹħ
    -0.21
    ä¸ĭè°ĥ
    -0.21
    ENUM
    -0.21
    —a
    -0.20
    uling
    -0.20
    POSITIVE LOGITS
     thereof
    0.42
     therein
    0.32
    ãģĿãĤĮãģ«
    0.29
    æĬĬå®ĥ
    0.27
     associated
    0.27
    åģļ人
    0.26
    ãģĿãĤĮãĤĴ
    0.25
    让å®ĥ
    0.25
    åĽłæѤ
    0.25
     therefore
    0.25
    Activations Density 0.174%

    No Known Activations