© 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. 28416
    Prev
    Next
    INDEX
    Explanations

    offering services, applications, or companies

    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
     fend
    -0.11
     attends
    -0.10
    alling
    -0.10
     Attend
    -0.09
    Delegate
    -0.09
     recounts
    -0.09
    urement
    -0.09
    eam
    -0.09
     [=
    -0.09
     interacts
    -0.09
    POSITIVE LOGITS
     offering
    0.21
     specializing
    0.18
     Offering
    0.16
     offer
    0.15
     listed
    0.14
     where
    0.14
     specialized
    0.13
     reviewed
    0.13
     employing
    0.12
     accepting
    0.12
    Activations Density 0.270%

    No Known Activations