© 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. 10609
    Prev
    Next
    INDEX
    Explanations

    FBI and Bureau investigations

    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
    æĶ¿åħļ
    -0.10
    _HC
    -0.10
    æĿĵ
    -0.10
    åħ¬è¯ģ
    -0.09
    åıŁ
    -0.09
    ิà¸ĩ
    -0.09
    满满
    -0.08
    èµIJ
    -0.08
    CTSTR
    -0.08
    å°ı康
    -0.08
    POSITIVE LOGITS
    åĮĹæĸ¹
    0.09
    æĪIJçĨŁ
    0.09
    åIJĮå¿ĥ
    0.08
    æīĵåĩ»
    0.08
    è´´
    0.08
     bure
    0.08
     доÑĢ
    0.08
    èģĶç½ij
    0.08
     FBI
    0.08
    .Primary
    0.08
    Activations Density 0.062%

    No Known Activations