© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53110
    Prev
    Next
    INDEX
    Explanations

    potential for

    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
    inton
    -0.09
    cheid
    -0.09
    Cancelable
    -0.09
     tù
    -0.09
    æĻ¯å¾·
    -0.09
    çĽĽå®´
    -0.09
    èĩ´åĬĽäºİ
    -0.08
    çĽĺçĤ¹
    -0.08
     Affero
    -0.08
    å®ŀè·µä¸Ń
    -0.08
    POSITIVE LOGITS
    æªIJ
    0.10
     unlimited
    0.09
    åĿıäºĨ
    0.09
    好æĦŁ
    0.09
    延伸
    0.09
    ç£ħ
    0.09
    æĽ´å¤ļ
    0.08
    å®Įåħ¨
    0.08
     further
    0.08
     lắm
    0.08
    Activations Density 0.060%

    No Known Activations