© 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. 54695
    Prev
    Next
    INDEX
    Explanations

    property ownership

    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
    æĤį
    -0.10
    åѦç§ij
    -0.09
    epad
    -0.09
    beck
    -0.09
     Verse
    -0.09
    èµ·æŃ¥
    -0.09
    é£İæ°Ķ
    -0.09
    æľĢåŁºæľ¬
    -0.09
    åħ¬ç½ijå®īå¤ĩ
    -0.09
    astes
    -0.09
    POSITIVE LOGITS
     ownership
    0.22
    æīĢæľīæĿĥ
    0.20
     Ownership
    0.20
    Ownership
    0.20
    ownership
    0.19
    产æĿĥ
    0.18
     owned
    0.17
     property
    0.15
     владелÑĮÑĨ
    0.15
    财产
    0.15
    Activations Density 0.102%

    No Known Activations