© 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. 58421
    Prev
    Next
    INDEX
    Explanations

    location and possession

    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
    ç½ijåıĭè¯Ħ论
    -0.09
    åĩºäºĨ
    -0.09
     должноÑģÑĤ
    -0.09
    æĬij
    -0.08
    åİĨåı²ä¸Ĭ
    -0.08
    ä¸ºæľŁ
    -0.08
    æľĿçĿĢ
    -0.08
    è·ĥ
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    ä¸į该
    -0.08
    POSITIVE LOGITS
    海岸
    0.11
    Reuse
    0.10
    çī½
    0.10
    çīµ
    0.10
     shores
    0.10
    æĶĿ
    0.10
    anges
    0.10
    çļĦè·Ŀ离
    0.10
    nearest
    0.09
    elog
    0.09
    Activations Density 0.096%

    No Known Activations