© 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. 49433
    Prev
    Next
    INDEX
    Explanations

    urban classification

    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
    nx
    -0.09
    s
    -0.08
    eder
    -0.08
    iu
    -0.08
    lish
    -0.08
     disob
    -0.08
    roid
    -0.08
    sb
    -0.08
    t
    -0.08
     Tomorrow
    -0.08
    POSITIVE LOGITS
    ization
    0.14
     legend
    0.14
     legends
    0.13
    ized
    0.13
    isation
    0.12
     renewal
    0.11
    izacion
    0.11
     Meyer
    0.11
    izing
    0.11
    izations
    0.11
    Activations Density 0.019%

    No Known Activations