© 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. 30573
    Prev
    Next
    INDEX
    Explanations

    this: followed by content type

    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
    è¿Ķ
    -0.09
    人æŃ»äº¡
    -0.09
    æī¹
    -0.09
    Center
    -0.08
    Bloc
    -0.08
    .tap
    -0.08
    incl
    -0.08
     Center
    -0.08
    arrow
    -0.08
    blo
    -0.07
    POSITIVE LOGITS
    ä¸ĢåŃĹ
    0.10
    éľİ
    0.09
    è¿Ļ段
    0.09
    å°½éĩı
    0.09
    è¿Ļ份
    0.09
    odus
    0.09
    .ak
    0.08
    ìĹij
    0.08
     ÑĦоÑĢ
    0.08
    elder
    0.08
    Activations Density 0.020%

    No Known Activations