© 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. 4993
    Prev
    Next
    INDEX
    Explanations

    lorem ipsum, wear, hairy, writing, dates

    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
     bans
    -0.10
     Vor
    -0.10
     sever
    -0.10
     disemb
    -0.09
    apat
    -0.09
    -det
    -0.09
    baz
    -0.09
    }></
    -0.09
    arez
    -0.09
    chwitz
    -0.09
    POSITIVE LOGITS
    iji
    0.10
     Tell
    0.09
    uis
    0.09
    ugu
    0.09
     Till
    0.08
     noticing
    0.08
     multin
    0.08
     Sig
    0.08
    arc
    0.08
     Maxim
    0.08
    Activations Density 0.005%

    No Known Activations