© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11115
    Prev
    Next
    INDEX
    Explanations

    location and proximity

    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
    å°ı康
    -0.10
    æ²®
    -0.10
    çĸ±
    -0.08
    æĭħå¿ĥ
    -0.08
    èİŀ
    -0.08
    åª
    -0.08
    é²ľ
    -0.08
    èķĥ
    -0.08
    彧
    -0.08
     aid
    -0.08
    POSITIVE LOGITS
    ä½įç½®
    0.13
    çļĦä½įç½®
    0.13
    atsu
    0.11
    .location
    0.11
    åľ°çIJĨä½įç½®
    0.11
    LOCATION
    0.11
     location
    0.11
    eus
    0.11
    ä¸įèĥ½åĨį
    0.11
     ÑĢаÑģполож
    0.10
    Activations Density 0.036%

    No Known Activations