© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27263
    Prev
    Next
    INDEX
    Explanations

    manner or way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    ook
    -0.12
    uala
    -0.11
    ipop
    -0.11
    owa
    -0.10
    AINS
    -0.10
    олÑı
    -0.10
     cred
    -0.10
     Ordering
    -0.10
    bil
    -0.09
     Wilkinson
    -0.09
    POSITIVE LOGITS
     manner
    0.39
     fashion
    0.33
     way
    0.23
     manners
    0.21
     Fashion
    0.21
    æĸ¹å¼ı
    0.20
     ways
    0.18
    -fashion
    0.16
    anner
    0.16
    Fashion
    0.15
    Activations Density 0.125%

    No Known Activations