© 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. 547
    Prev
    Next
    INDEX
    Explanations

    people, Ghost, precepts, peace, Simon, feast, called

    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
    å¨Ħ
    -0.24
     perms
    -0.23
    ehr
    -0.23
     :=↵
    -0.23
    ords
    -0.22
    ELL
    -0.22
    danger
    -0.22
    ächt
    -0.22
    æŶéĹ´åĴĮ
    -0.22
    pies
    -0.22
    POSITIVE LOGITS
    åĽłä¸ºä»ĸ们
    0.23
    .""
    0.22
    bury
    0.21
    çĶļ
    0.21
    lds
    0.21
    åIJĦçľģ
    0.21
    æľºåĪ¶
    0.20
     reimb
    0.20
    umb
    0.20
     omnip
    0.20
    Activations Density 0.147%

    No Known Activations