© 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. 23372
    Prev
    Next
    INDEX
    Explanations

    travel

    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
    é¦ĸ次
    -0.09
    èįīèİĵ
    -0.09
    rive
    -0.08
    кÑĢÑĥÑĤ
    -0.08
    emas
    -0.08
    (s
    -0.08
    quat
    -0.08
     trading
    -0.07
    å¾¹
    -0.07
    ç»
    -0.07
    POSITIVE LOGITS
    .contentSize
    0.10
    _Word
    0.10
    çĶ¨åĵģ
    0.10
    ogue
    0.10
    èĢħçļĦ
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    èĢħ
    0.09
    prising
    0.09
    .photos
    0.09
    onica
    0.09
    Activations Density 0.026%

    No Known Activations