© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    exclude word

    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
    åħ´èµ·
    -0.25
     decrease
    -0.23
    æ´»çĿĢ
    -0.20
    heet
    -0.19
    ÑĢид
    -0.19
    å¥łåŁº
    -0.18
    ä¸Ńåħ±
    -0.18
    heets
    -0.18
    heed
    -0.18
    è¾īçħĮ
    -0.18
    POSITIVE LOGITS
    ively
    0.28
    halb
    0.25
     khá»ıi
    0.24
    aption
    0.24
    ted
    0.23
    åŁ
    0.23
    ä»»ä½ķ
    0.23
    ä¸ĢåĪĩ
    0.22
    ivity
    0.22
    tal
    0.22
    Activations Density 0.018%

    No Known Activations