© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3180
    Prev
    Next
    INDEX
    Explanations

    discrete or discreet

    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
    Negative Logits
    ays
    -0.23
    æŨ
    -0.20
    éĻħ
    -0.19
    åħ·
    -0.19
    strom
    -0.18
    ļ
    -0.18
     Sachs
    -0.18
    itter
    -0.18
    strand
    -0.18
    arms
    -0.17
    POSITIVE LOGITS
    ely
    0.31
    aneous
    0.27
    ively
    0.25
    -minded
    0.22
    orial
    0.21
     minded
    0.21
    nÃŃ
    0.21
    orro
    0.21
    emente
    0.21
    arily
    0.21
    Activations Density 0.008%

    No Known Activations