© 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. 89871
    Prev
    Next
    INDEX
    Explanations

    `scape` `Streets` `ved`

    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
    erot
    -0.12
     sometime
    -0.09
    som
    -0.09
    agle
    -0.09
    ancel
    -0.09
     occasion
    -0.08
    .xmlbeans
    -0.08
    aby
    -0.08
     somew
    -0.08
    ±Ð¾ÑĤ
    -0.08
    POSITIVE LOGITS
    âĶģâĶģ
    0.10
    CDATA
    0.10
    ç½
    0.09
     tad
    0.09
    agra
    0.09
     scape
    0.09
    ients
    0.09
    ved
    0.09
     Streets
    0.09
    áºŃn
    0.09
    Activations Density 0.067%

    No Known Activations