© 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. 3787
    Prev
    Next
    INDEX
    Explanations

    share with others

    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
     Howell
    -0.12
    itar
    -0.11
    ridge
    -0.11
    è¯Ŀ
    -0.11
     casually
    -0.10
     tin
    -0.10
    iram
    -0.10
    ê²Į
    -0.09
     inspector
    -0.09
     Reflect
    -0.09
    POSITIVE LOGITS
     us
    0.18
     others
    0.16
     readers
    0.12
    others
    0.12
     audiences
    0.11
     Others
    0.10
    Others
    0.10
     hungry
    0.10
     interested
    0.10
     starving
    0.09
    Activations Density 0.016%

    No Known Activations