© 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. 38802
    Prev
    Next
    INDEX
    Explanations

    abstract nouns followed by 'of'

    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
    ausal
    -0.08
    é»İæĺİ
    -0.08
    des
    -0.08
    èªĵè¨Ģ
    -0.08
    æµĵæµĵçļĦ
    -0.08
    äºļåĨĽ
    -0.08
    è¯Ĵ
    -0.08
    addresses
    -0.08
    aisy
    -0.08
    åıĮæīĭ
    -0.08
    POSITIVE LOGITS
    abler
    0.09
    ç¬ı
    0.09
     Colbert
    0.09
     пÑĢинÑıл
    0.09
    Pok
    0.09
    ucken
    0.08
    éĥ¢
    0.08
    ableView
    0.08
    å°±åľ¨äºİ
    0.08
    less
    0.08
    Activations Density 0.079%

    No Known Activations