© 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. 6558
    Prev
    Next
    INDEX
    Explanations

    Moore and similar names

    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
    mes
    -0.11
     ober
    -0.10
    er
    -0.10
     Wit
    -0.09
    loc
    -0.09
     pause
    -0.09
    lya
    -0.09
     Pause
    -0.09
    pa
    -0.09
    chter
    -0.08
    POSITIVE LOGITS
    heed
    0.11
     inward
    0.11
     Catal
    0.10
     aloud
    0.09
    gaard
    0.09
     Cummings
    0.09
     Isis
    0.09
     deeply
    0.09
     louder
    0.09
    antas
    0.09
    Activations Density 0.002%

    No Known Activations