© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2437
    Prev
    Next
    INDEX
    Explanations

    product identifier SKU

    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
    zelf
    -0.22
    asz
    -0.22
     keen
    -0.20
    ä¸Ŀè·¯
    -0.20
    UIS
    -0.19
    imony
    -0.19
    亥
    -0.19
     scholar
    -0.19
    MimeType
    -0.19
    oce
    -0.18
    POSITIVE LOGITS
    edi
    0.24
    çłģ
    0.23
     SKU
    0.23
    edin
    0.22
    çĶŁé²ľ
    0.21
    ä¸ĸä¸Ĭ
    0.21
    æŃ£ç¢º
    0.20
    getter
    0.20
    variation
    0.20
     Sunny
    0.19
    Activations Density 0.003%

    No Known Activations