© 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. 2541
    Prev
    Next
    INDEX
    Explanations

    locations in US states

    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
    ñe
    -0.27
    å¾Ģäºĭ
    -0.24
     sooner
    -0.24
    缸åħ³ä¿¡æģ¯
    -0.23
    ñ
    -0.23
    è¿Ļæī¹
    -0.23
    ä¸ĢåĪĻ
    -0.22
    Someone
    -0.22
    ãģıãĤĮ
    -0.22
    oldt
    -0.22
    POSITIVE LOGITS
    éģįåıĬ
    0.37
    éģįå¸ĥ
    0.36
    å¢ŀèĩ³
    0.30
    åħ±è®¡
    0.30
    åħ±æľī
    0.28
    ilib
    0.26
    åħ±
    0.26
     spanning
    0.25
    irteen
    0.25
     totaling
    0.24
    Activations Density 0.041%

    No Known Activations