© 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. 88645
    Prev
    Next
    INDEX
    Explanations

    describing qualities and comparisons

    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
    cem
    -0.09
    PR
    -0.08
     Yourself
    -0.08
    .."
    -0.08
    ulp
    -0.08
    vd
    -0.08
    .""
    -0.08
    charm
    -0.08
     Cherry
    -0.08
    itive
    -0.08
    POSITIVE LOGITS
     reviewers
    0.15
     researchers
    0.14
     people
    0.14
    obody
    0.13
     analysts
    0.13
     authorities
    0.12
     scientists
    0.12
     portions
    0.12
     majority
    0.12
     companies
    0.12
    Activations Density 0.682%

    No Known Activations