© 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. 21806
    Prev
    Next
    INDEX
    Explanations

    iraq

    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
    ÑģÑĮ
    -0.10
    edata
    -0.10
    odal
    -0.09
    ãģıãĤĭ
    -0.08
    æħĭ
    -0.08
    ç¼ķ
    -0.08
    举æŃ¢
    -0.08
     СанкÑĤ
    -0.08
    uart
    -0.07
    å¤Ħ
    -0.07
    POSITIVE LOGITS
     Kurdistan
    0.12
     Rudd
    0.10
    istan
    0.10
    iness
    0.10
    ted
    0.10
    -American
    0.10
    unk
    0.09
    ision
    0.09
    ripp
    0.09
    TagName
    0.09
    Activations Density 0.016%

    No Known Activations