© 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. 28030
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    çĶŁäº§åĬĽ
    -0.09
    ster
    -0.09
    cul
    -0.09
    heimer
    -0.09
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    r
    -0.08
    为ä»Ģä¹Īè¦ģ
    -0.08
    éľĢè¦ģçĶ¨
    -0.08
    éĿĽ
    -0.08
    csr
    -0.08
    POSITIVE LOGITS
    endon
    0.11
    è¶³å¤Ł
    0.10
    ä¸Ģå¥Ĺ
    0.09
    åıªéľĢ
    0.09
    æŀģå°ij
    0.09
    HeaderCode
    0.09
    ä¸Ģåı¥
    0.09
    å°ijéĩı
    0.09
    تصÙģ
    0.09
    emble
    0.09
    Activations Density 0.028%

    No Known Activations