© 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. 62849
    Prev
    Next
    INDEX
    Explanations

    units of length

    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
    ä¸Ģè§Ĵ
    -0.10
    ä¸į代表
    -0.09
    åĺĺ
    -0.09
    ç¬ijç¬ij
    -0.09
    ä¾ĽåĽ¾
    -0.09
    éĢłçº¸
    -0.09
    åģĥ
    -0.09
    ä»Ħ
    -0.08
    æĬĢæľ¯åĴĮ
    -0.08
    bay
    -0.08
    POSITIVE LOGITS
    ynes
    0.09
    rote
    0.09
    å¼ĺ
    0.09
    rig
    0.09
    èľľ
    0.09
    å¼¥
    0.09
    æł¾
    0.09
     GENERATED
    0.08
     VIR
    0.08
     ohio
    0.08
    Activations Density 0.041%

    No Known Activations