© 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. 17193
    Prev
    Next
    INDEX
    Explanations

    former Yugoslavia region

    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
    缴è¾ĸ
    -0.09
    gis
    -0.09
     оÑĤзÑĭвÑĭ
    -0.09
    ady
    -0.08
    åĮ¡
    -0.08
    ike
    -0.08
     mary
    -0.08
    ળ
    -0.08
     açık
    -0.08
    æ«ĥ
    -0.08
    POSITIVE LOGITS
     Macedonia
    0.09
     Bosnia
    0.09
     Balk
    0.09
    ASE
    0.09
    å¿į
    0.09
    æ´²
    0.09
    å¾ĪæŃ£å¸¸
    0.09
     Yugosl
    0.09
    çľĭåĪ°äºĨ
    0.08
    æī¬å·ŀ
    0.08
    Activations Density 0.118%

    No Known Activations