© 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. 633
    Prev
    Next
    INDEX
    Explanations

    gladiatorial adventure, tango dancing, Andalusians

    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
    ä½ij
    -0.23
    çĶ¥
    -0.23
    åħ¥åѦ
    -0.22
     Deng
    -0.22
     Collider
    -0.22
     BTN
    -0.22
    claimer
    -0.22
    èĤĦ
    -0.22
    filesize
    -0.22
    #undef
    -0.22
    POSITIVE LOGITS
    åĽŀäºĭ
    0.26
    å¸Ĩ
    0.25
     flam
    0.24
    æĪıåī§
    0.23
     Tickets
    0.23
    åĪĢ
    0.23
     stabbing
    0.23
     sare
    0.23
    åİħ
    0.23
     guitarist
    0.22
    Activations Density 0.003%

    No Known Activations