© 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. 996
    Prev
    Next
    INDEX
    Explanations

    IP, ID, E, OD, Q, News

    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
    èģĮä¸ļçĶŁæ¶¯
    -0.23
     seas
    -0.23
    nown
    -0.21
    MBED
    -0.21
    á»ıi
    -0.20
     ausp
    -0.20
    ju
    -0.20
     Rolls
    -0.20
    tip
    -0.20
    æĦıä¹īä¸Ĭ
    -0.20
    POSITIVE LOGITS
    ervice
    0.23
    客æĪ·æľįåĬ¡
    0.23
    -enabled
    0.23
    è¹ĩ
    0.22
    acco
    0.22
    Providers
    0.22
    å¸Ń
    0.22
    ervers
    0.22
    .provider
    0.22
    _dbg
    0.21
    Activations Density 0.002%

    No Known Activations