© 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. 90806
    Prev
    Next
    INDEX
    Explanations

    services and products

    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
    -services
    -0.16
     SERVICES
    -0.16
    Services
    -0.14
     services
    -0.14
    services
    -0.13
     Services
    -0.13
    _services
    -0.13
     servicing
    -0.13
    .ylabel
    -0.12
    .services
    -0.12
    POSITIVE LOGITS
    xis
    0.10
     Polit
    0.10
     ¶
    0.09
     Banana
    0.09
    EDIA
    0.09
    EDI
    0.09
    .Exec
    0.08
    upro
    0.08
     flatt
    0.08
     Mo
    0.08
    Activations Density 0.344%

    No Known Activations