© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    names of people followed by titles or actions

    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
    缼åħ¸
    -0.09
    éĻ¢éĻ¢éķ¿
    -0.09
    è§ī
    -0.09
    uant
    -0.09
    EventData
    -0.09
    å®Ĺ
    -0.09
     LSM
    -0.08
    æī°ä¹±
    -0.08
    INGTON
    -0.08
    åĺ»åĺ»
    -0.08
    POSITIVE LOGITS
     ноÑĩ
    0.10
    ikit
    0.09
    onas
    0.09
    æī§æĶ¿
    0.09
    \Bridge
    0.09
    åī¯
    0.09
    笪
    0.08
    æī§æ³ķ
    0.08
    èIJ¼
    0.08
     Jelly
    0.08
    Activations Density 0.099%

    No Known Activations