© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    barcode, ISBN, or product codes

    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
    msgs
    -0.27
    apr
    -0.23
    æŁIJç§įç¨ĭ度
    -0.23
    /tasks
    -0.22
    orta
    -0.22
    åĨ²
    -0.22
     homosex
    -0.22
     motions
    -0.22
    ascade
    -0.21
    ç»¿åľ°
    -0.21
    POSITIVE LOGITS
    æł¼å¼ı
    0.31
     barcode
    0.31
    łģ
    0.30
     checksum
    0.30
    Barcode
    0.29
     ISBN
    0.28
    -length
    0.27
    decimal
    0.27
     Moment
    0.27
    Decimal
    0.26
    Activations Density 0.014%

    No Known Activations