© 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. 7304
    Prev
    Next
    INDEX
    Explanations

    surviving, survived, transl

    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
    fir
    -0.10
    isode
    -0.10
    åģĩæĹ¥
    -0.08
    åħ¨åŁŁ
    -0.08
    strain
    -0.08
     limp
    -0.08
    浸
    -0.08
     Stem
    -0.08
    immutable
    -0.08
    é©·
    -0.08
    POSITIVE LOGITS
    åł¡
    0.09
    è¿ĩå¾Ģ
    0.09
    èĤº
    0.09
    عÙĦا
    0.08
    endants
    0.08
    inations
    0.08
    ry
    0.08
    å¢ŀè¿Ľ
    0.08
     cul
    0.08
    åIJŀ
    0.08
    Activations Density 0.001%

    No Known Activations