© 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. 1013
    Prev
    Next
    INDEX
    Explanations

    keys to

    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
    irm
    -0.24
    pun
    -0.23
    uais
    -0.23
    头顶
    -0.22
     Colomb
    -0.22
     inflicted
    -0.22
    ENSE
    -0.22
    çļĦèĦ¸
    -0.22
    opher
    -0.21
    éģµ
    -0.21
    POSITIVE LOGITS
    éĴ¥åĮĻ
    0.39
     locker
    0.32
     Unlock
    0.28
    ðŁĶij
    0.27
     keys
    0.27
     unlock
    0.27
     unlocking
    0.26
     drawers
    0.26
     esc
    0.25
    æı¡
    0.25
    Activations Density 0.022%

    No Known Activations