© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28322
    Prev
    Next
    INDEX
    Explanations

    short lived, pair of, awful lot of

    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
     foc
    -0.17
     authorised
    -0.16
     manoe
    -0.16
     initialised
    -0.15
     honour
    -0.14
     fibre
    -0.14
     centre
    -0.14
     Honour
    -0.14
     behaviours
    -0.14
     flavours
    -0.13
    POSITIVE LOGITS
     totally
    0.11
     Alto
    0.10
    tot
    0.10
     apart
    0.09
     possibly
    0.09
     viz
    0.09
    possibly
    0.09
    viz
    0.09
    Tot
    0.09
     Trevor
    0.09
    Activations Density 0.225%

    No Known Activations