© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    street names

    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
    æĢ§çļĦ
    -0.27
    NESS
    -0.26
    ascript
    -0.23
    ä¹ĭå¤Ħ
    -0.22
    æľŁåĨħ
    -0.22
     logically
    -0.22
    éľĩæħij
    -0.22
    éĻIJ度
    -0.21
    !("
    -0.21
    /control
    -0.21
    POSITIVE LOGITS
     residents
    0.25
     campus
    0.24
    ä¸Ģ带
    0.24
    former
    0.24
    gne
    0.23
    转弯
    0.23
     Ger
    0.23
     former
    0.22
     Bere
    0.22
     excav
    0.22
    Activations Density 0.023%

    No Known Activations