© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 196
    Prev
    Next
    INDEX
    Explanations

    risk quantification

    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
    iture
    -0.25
     Depos
    -0.24
    alu
    -0.24
    æ·±åħ¥
    -0.23
    arty
    -0.23
    çĤĢ
    -0.23
    .depth
    -0.23
     warmly
    -0.23
    _switch
    -0.22
    深度
    -0.22
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.67
     probability
    0.66
     probabilities
    0.63
    çļĦæ¦Ĥçİĩ
    0.59
     statistically
    0.55
    Probability
    0.54
    åĩłçİĩ
    0.54
    probability
    0.54
     Probability
    0.50
     proportion
    0.47
    Activations Density 0.166%

    No Known Activations