© 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. 57667
    Prev
    Next
    INDEX
    Explanations

    in or from or to or 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
    说è¯Ŀ
    -0.08
    éĿ³
    -0.08
    elog
    -0.08
    urope
    -0.08
     unnamed
    -0.08
    èµĪ
    -0.07
    oker
    -0.07
    /upload
    -0.07
     BASIS
    -0.07
    ammen
    -0.07
    POSITIVE LOGITS
    ä¸įå°½
    0.12
    alue
    0.10
    å¤Ļ
    0.10
    ayed
    0.10
    ä¼Łå¤§çļĦ
    0.10
    å°±è¿Ļä¹Ī
    0.10
    è¿ĻäºĽä¸ľè¥¿
    0.09
    åīįéĢĶ
    0.09
    è§Ħéģ¿
    0.09
     falta
    0.09
    Activations Density 0.041%

    No Known Activations