© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    bath and tub

    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
    é«ĺé¢ij
    -0.24
    å°ijæķ°
    -0.23
    rtl
    -0.23
    强è¡Į
    -0.23
    stakes
    -0.23
    身价
    -0.23
     agricult
    -0.22
    mill
    -0.22
    æ°ijå¿ĥ
    -0.22
    streams
    -0.21
    POSITIVE LOGITS
    åį§
    0.27
    ption
    0.24
     loung
    0.23
    溢
    0.23
     upstairs
    0.23
    urniture
    0.22
    èģĶéĢļ
    0.22
    å¥ĹæĪ¿
    0.22
     tub
    0.22
     shape
    0.22
    Activations Density 0.002%

    No Known Activations