© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52933
    Prev
    Next
    INDEX
    Explanations

    possessive adjectives

    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
    æ¶İ
    -0.10
    é¼ĵ
    -0.10
     assort
    -0.09
    uro
    -0.09
    å°±æľīäºĨ
    -0.09
    ialized
    -0.09
    俾
    -0.09
    icot
    -0.08
    bson
    -0.08
    ä¸Ģ代
    -0.08
    POSITIVE LOGITS
    èIJ¥ä¸ļæī§çħ§
    0.10
    èŀ
    0.09
    åį°
    0.09
    _pet
    0.09
    å¼ĢéĢļ
    0.09
    ÑģÑĤв
    0.09
    驾驶è¯ģ
    0.08
     влаÑģÑĤи
    0.08
    åĪĽéĢłåĬĽ
    0.08
    çĻ«çĹ«çĹħ
    0.08
    Activations Density 0.120%

    No Known Activations