© 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. 91058
    Prev
    Next
    INDEX
    Explanations

    changes in

    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
    REA
    -0.12
    iken
    -0.12
     heraus
    -0.11
    rete
    -0.11
    Rand
    -0.11
    ushima
    -0.11
     prof
    -0.10
    coil
    -0.10
     reco
    -0.10
     Piper
    -0.10
    POSITIVE LOGITS
    /extensions
    0.17
     caused
    0.11
    /var
    0.11
    (changes
    0.11
     occur
    0.11
    /problems
    0.11
     in
    0.11
     occurring
    0.10
    /dev
    0.10
     occurred
    0.10
    Activations Density 0.402%

    No Known Activations