© 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. 962
    Prev
    Next
    INDEX
    Explanations

    Copyright notices, file IDs, abstract

    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
    _present
    -0.26
     present
    -0.25
    otel
    -0.25
    Present
    -0.25
    present
    -0.23
     vá»ijn
    -0.23
    -present
    -0.23
    èijĽ
    -0.22
     dine
    -0.22
    Duplicate
    -0.22
    POSITIVE LOGITS
    以åIJİ
    0.25
     afterward
    0.24
    èī¯
    0.23
    (Print
    0.23
    gebra
    0.22
    è½¹
    0.22
    @qq
    0.22
    åĸľæ¬¢åIJĥ
    0.21
    ä¸įåģľçļĦ
    0.21
    ewise
    0.21
    Activations Density 0.001%

    No Known Activations