© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    terrace or deck

    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
    errupt
    -0.22
    soever
    -0.21
    ARP
    -0.20
    æİĸ
    -0.20
    seed
    -0.20
     pathetic
    -0.19
    xA
    -0.19
     Kingdom
    -0.19
     lump
    -0.19
    æľīæĿ¡ä»¶çļĦ
    -0.19
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.32
    /column
    0.26
     overlooking
    0.26
    ä¸Ĭæľī
    0.26
    -mounted
    0.24
    /table
    0.24
    éĺ³åı°
    0.23
    Ħ
    0.22
    éĿ¢ä¸Ĭ
    0.22
    /bar
    0.22
    Activations Density 0.007%

    No Known Activations