© 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. 48600
    Prev
    Next
    INDEX
    Explanations

    effect, dynasty, Church, Party, API, formation

    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
    -0.11
    们çļĦ
    -0.11
    åĢij
    -0.11
    们éĥ½
    -0.10
    à¹Ĩ
    -0.10
     à¹Ĩ
    -0.09
    äºĨä¸Ģéģį
    -0.09
    pard
    -0.09
    gars
    -0.08
    standen
    -0.08
    POSITIVE LOGITS
    éļĪ
    0.11
    åĨħçļĦ
    0.10
    åī¯æľ¬
    0.08
    éĤ£ç§į
    0.08
    å®Ĺ
    0.08
    /operator
    0.08
    è¿ĻçĤ¹
    0.08
     اÙĦÙĥرÙĬÙħ
    0.08
    ä¹łæĥ¯
    0.08
    pecific
    0.08
    Activations Density 0.549%

    No Known Activations