© 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. 19209
    Prev
    Next
    INDEX
    Explanations

    quoting or citing information

    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
    å¼ĢèįĴ
    -0.10
    ISS
    -0.10
    èĪªå¤©
    -0.09
     Reviewed
    -0.09
    ä¼¼
    -0.09
    å¸Ļ
    -0.08
    åĪ¶æĪIJ
    -0.08
    \Module
    -0.08
     оÑģоб
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.11
    æijĺè¦ģ
    0.11
     sobie
    0.10
    åİŁæĸĩ
    0.10
    ï¼ļ“
    0.10
    ä»ĸ说
    0.08
    åħ³äºİ
    0.08
    terr
    0.08
    lear
    0.08
    æIJIJ
    0.08
    Activations Density 0.136%

    No Known Activations