© 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. 454
    Prev
    Next
    INDEX
    Explanations

    "Yes" or "No" answers

    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
     popular
    -0.31
     proudly
    -0.28
    åIJĦå¼ı
    -0.27
     tip
    -0.27
     thousands
    -0.25
     brass
    -0.25
    åIJĦç§į
    -0.24
     stories
    -0.24
     hundreds
    -0.23
     forever
    -0.23
    POSITIVE LOGITS
    çIJĨçĶ±
    0.45
    åİŁåĽłæĺ¯
    0.38
    çļĦçIJĨçĶ±
    0.38
     reasoning
    0.35
    åIJĪçIJĨæĢ§
    0.34
    _REASON
    0.34
    åĪĨæŀIJ
    0.33
     reason
    0.32
    åĽłä¸ºåľ¨
    0.32
    åĽłä¸ºæĪij
    0.32
    Activations Density 0.036%

    No Known Activations