© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114680
    Prev
    Next
    INDEX
    Explanations

    street mining

    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
     Delegate
    -0.10
     ep
    -0.09
     feminine
    -0.09
     accent
    -0.09
    zia
    -0.09
     mel
    -0.09
     screws
    -0.09
     inert
    -0.09
    ARE
    -0.09
     swim
    -0.08
    POSITIVE LOGITS
     street
    0.25
     Street
    0.20
    street
    0.18
    Street
    0.18
     STREET
    0.18
    _street
    0.14
     streets
    0.14
     Streets
    0.13
     roadside
    0.12
    .street
    0.12
    Activations Density 0.001%

    No Known Activations