© 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. 19173
    Prev
    Next
    INDEX
    Explanations

    cities in Iraq and Syria

    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
    们
    -0.10
    andes
    -0.10
    éħIJ
    -0.10
    west
    -0.09
     Pathfinder
    -0.09
    ä¸Ģå¤Ħ
    -0.09
    æ°´çĶµ
    -0.09
    水产
    -0.09
    æĸĭ
    -0.09
    天åłĤ
    -0.08
    POSITIVE LOGITS
    èĥ§
    0.09
     Nug
    0.09
    BuilderFactory
    0.08
    æĤį
    0.08
    æľĪä¸ĭ
    0.08
    hots
    0.08
    æģ¶æĢ§
    0.08
    ãģĹãģ¾ãģĨ
    0.08
    borough
    0.08
    éģĺ
    0.08
    Activations Density 0.005%

    No Known Activations