© 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. 21278
    Prev
    Next
    INDEX
    Explanations

    our followed by possessives

    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
    æ²ī
    -0.10
    ä¾Ī
    -0.09
     themselves
    -0.08
    æŁıæŀĹ
    -0.08
    uzzi
    -0.08
    çīĮåŃIJ
    -0.08
     diss
    -0.08
     Ñģами
    -0.08
    иÑĤа
    -0.08
    åIJĪä¸Ģ
    -0.08
    POSITIVE LOGITS
    追究
    0.09
    å¸ļ
    0.09
    æ°´æĻ¶
    0.09
    å±±ä¸Ĭ
    0.09
    å®ŀè´¨æĢ§
    0.09
    çIJīçĴĥ
    0.09
    .Decode
    0.08
    åıµ
    0.08
    pw
    0.08
    UpDown
    0.08
    Activations Density 0.026%

    No Known Activations