© 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. 55319
    Prev
    Next
    INDEX
    Explanations

    place names ending in ley, ely, land, bridge, dale, or eway

    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
    ollen
    -0.10
    çij°
    -0.10
    è¿Ļæĸ¹éĿ¢
    -0.10
    å¯Ł
    -0.10
    .literal
    -0.09
     пÑĢеп
    -0.09
    agher
    -0.09
     Meadows
    -0.09
    enance
    -0.09
    avid
    -0.09
    POSITIVE LOGITS
    aldi
    0.09
    ope
    0.09
    encies
    0.09
    vro
    0.09
    ency
    0.08
    鬲
    0.08
    åĩ¡äºĭ
    0.08
    éªĸ
    0.08
    cip
    0.08
    ä¼ĹæīĢ
    0.08
    Activations Density 0.005%

    No Known Activations