© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    suspicious or screw

    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
    ting
    -0.21
    å¾Īæ£Ĵ
    -0.21
    forth
    -0.21
    ross
    -0.20
    \/\/
    -0.20
    è¾ĥ好çļĦ
    -0.20
    propri
    -0.19
     cush
    -0.19
    ä¸ĩçī©
    -0.19
    åħ³æĢĢ
    -0.19
    POSITIVE LOGITS
    iest
    0.26
    -minded
    0.23
     logs
    0.21
    iness
    0.20
     minded
    0.20
    ous
    0.20
    åĩ«
    0.20
    /conf
    0.20
    fish
    0.20
    ç½ij讯
    0.19
    Activations Density 0.007%

    No Known Activations