© 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. 167
    Prev
    Next
    INDEX
    Explanations

    herniated / hernia

    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
    rum
    -0.24
    Dou
    -0.23
    cir
    -0.21
     flown
    -0.21
    usher
    -0.20
    expand
    -0.20
    etal
    -0.20
    åĴĮåľ°åĮº
    -0.20
    istr
    -0.20
    çĭIJ
    -0.20
    POSITIVE LOGITS
    ½
    0.22
    PIPE
    0.21
    å´®
    0.21
    ķ
    0.21
    ion
    0.20
    ç¬ı
    0.20
    aine
    0.20
    ugu
    0.20
    æŀķ头
    0.20
     Marl
    0.19
    Activations Density 0.017%

    No Known Activations