© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    states and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æ¿Ģèµ·
    -0.10
    heck
    -0.09
     Rey
    -0.09
    жи
    -0.09
    éĩįå¤į
    -0.09
    å´Ĥ
    -0.09
     Confidential
    -0.08
    åIJĦåĽ½
    -0.08
    çݯçIJĥ
    -0.08
    æ±¾
    -0.08
    POSITIVE LOGITS
     states
    0.14
    çľģ份
    0.12
     state
    0.12
    æĪijçľģ
    0.12
    <State
    0.11
     California
    0.11
     States
    0.11
    getState
    0.11
    å·ŀ
    0.11
    .getState
    0.11
    Activations Density 0.168%

    No Known Activations