© 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. 19799
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

    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
    zá
    -0.09
    ä¸ĢåŃĹ
    -0.09
    edes
    -0.09
    erson
    -0.09
    eded
    -0.08
    edic
    -0.08
    ersions
    -0.08
     Curl
    -0.08
     hob
    -0.07
    _mentions
    -0.07
    POSITIVE LOGITS
    à¹Ģà¸Ń
    0.10
    è¹Ĭ
    0.10
    姿
    0.09
    coli
    0.09
    åıįæĦŁ
    0.09
    æıĨ
    0.09
    ULD
    0.09
    å¾®éĩıåħĥç´ł
    0.09
    解æķ£
    0.09
    åīįçŀ»
    0.09
    Activations Density 0.116%

    No Known Activations