© 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. 88599
    Prev
    Next
    INDEX
    Explanations

    Part followed by roman numerals

    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
     stagger
    -0.09
    cred
    -0.08
    quot
    -0.07
     Anc
    -0.07
     sap
    -0.07
    andard
    -0.07
    _unicode
    -0.06
     knee
    -0.06
     Running
    -0.06
     Congratulations
    -0.06
    POSITIVE LOGITS
     Part
    0.15
     III
    0.15
     II
    0.14
    III
    0.12
     VII
    0.12
     iii
    0.11
    Part
    0.11
     XI
    0.11
     Moran
    0.11
     Pt
    0.11
    Activations Density 0.012%

    No Known Activations