© 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. 31956
    Prev
    Next
    INDEX
    Explanations

    increase and growth

    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
    AKER
    -0.11
    onne
    -0.11
     Bip
    -0.11
    ishly
    -0.10
    ä¸įåŃĺåľ¨
    -0.10
     ev
    -0.10
     Levin
    -0.09
     cach
    -0.09
     strongest
    -0.09
     Jou
    -0.09
    POSITIVE LOGITS
     increased
    0.17
     increasing
    0.15
     increases
    0.14
    incre
    0.14
     increase
    0.13
     decreased
    0.13
     unprecedented
    0.12
     underestimated
    0.12
     Increased
    0.12
     greater
    0.12
    Activations Density 0.385%

    No Known Activations