© 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. 4788
    Prev
    Next
    INDEX
    Explanations

    adjective describing condition or state

    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
    æĦ
    -0.09
    stance
    -0.09
    åħĨ
    -0.09
    Registers
    -0.08
     ank
    -0.08
    /accounts
    -0.08
     matter
    -0.08
    æĬķèŀįèµĦ
    -0.08
    stakes
    -0.08
    çĿĽ
    -0.08
    POSITIVE LOGITS
    çļĦåij½è¿IJ
    0.10
    çĶ¨å¾®ä¿¡
    0.09
    æī§æĦı
    0.09
    æĭ¥
    0.09
    åħ¨éĿ¢èIJ½å®ŀ
    0.09
    odem
    0.09
    åĨ²åĬ¨
    0.09
    å¨Ī
    0.09
    _pf
    0.08
    à´±
    0.08
    Activations Density 0.071%

    No Known Activations