© 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. 26992
    Prev
    Next
    INDEX
    Explanations

    Scala, `.com`, Park

    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
    æľĢå¤ļ
    -0.10
    æīĵä»Ĺ
    -0.09
    fell
    -0.08
    eworld
    -0.08
    深度
    -0.08
    _PROPERTIES
    -0.08
    éĢĥè·ij
    -0.08
    Ùħست
    -0.08
    	effect
    -0.08
     effect
    -0.07
    POSITIVE LOGITS
    éªĸ
    0.10
    å±IJ
    0.09
    çħ§äº®
    0.09
    nels
    0.09
    好çľĭ
    0.09
    ets
    0.09
    ä¸į该
    0.09
    ippers
    0.08
    çľĭå¾ħ
    0.08
     голоÑģ
    0.08
    Activations Density 0.368%

    No Known Activations