© 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. 35980
    Prev
    Next
    INDEX
    Explanations

    external links or special characters

    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
    为ä¸Ģä½ĵçļĦ
    -0.08
    æ»ĩ
    -0.08
     Innoc
    -0.08
    imeo
    -0.08
    Ùģاع
    -0.08
    å®ģæĦ¿
    -0.07
    ç½®æį¢
    -0.07
    Ñģоедин
    -0.07
    èĢĮè¨Ģ
    -0.07
    .println
    -0.07
    POSITIVE LOGITS
    æĬŁ
    0.10
    _PREF
    0.09
    Wiki
    0.09
    iju
    0.09
    åį¿
    0.08
    ä¼ĺèī¯
    0.08
    éŨåīį
    0.08
     External
    0.08
    å¯Ĵåģĩ
    0.08
     sanction
    0.08
    Activations Density 0.123%

    No Known Activations