© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52228
    Prev
    Next
    INDEX
    Explanations

    familiar with

    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
    工夫
    -0.09
    èħIJ
    -0.09
    isia
    -0.09
    utable
    -0.09
    anke
    -0.09
    é»ijçĻ½
    -0.09
    obot
    -0.08
    ç®Ģä»ĭ
    -0.08
    ouse
    -0.08
    Bid
    -0.08
    POSITIVE LOGITS
     format
    0.10
    ä¹łæĥ¯äºĨ
    0.10
    çĨŁæĤīçļĦ
    0.10
    çĨŁæĤī
    0.10
     familiar
    0.10
    亲è¿ij
    0.09
    å°Ķæĸ¯
    0.09
     unfamiliar
    0.09
     formats
    0.09
    èµĸ
    0.08
    Activations Density 0.026%

    No Known Activations