© 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. 58859
    Prev
    Next
    INDEX
    Explanations

    connection, bond, attachment

    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
    大åħ¨
    -0.09
    èħĶ
    -0.09
    æİ¥è¿ij
    -0.08
    åĬŃ
    -0.08
    mani
    -0.08
    rippling
    -0.08
    ØŃا
    -0.08
    anko
    -0.08
    åħ¨å¥Ĺ
    -0.08
     continental
    -0.08
    POSITIVE LOGITS
    纽带
    0.21
     bond
    0.14
    åĢºåĪ¸
    0.14
     bonds
    0.13
    çīµæĮĤ
    0.13
     ties
    0.12
    强çĥĪçļĦ
    0.12
    èIJ¦
    0.12
    ç¾ģ
    0.12
    .tie
    0.11
    Activations Density 0.045%

    No Known Activations