© 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. 113150
    Prev
    Next
    INDEX
    Explanations

    modifying user, absorbing electron, hiring company

    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
     chim
    -0.10
    -deals
    -0.10
     merger
    -0.10
     rever
    -0.09
    ocht
    -0.09
    ninger
    -0.09
     eks
    -0.09
    ools
    -0.09
    Soup
    -0.09
     Geh
    -0.09
    POSITIVE LOGITS
    èĢħ
    0.19
     party
    0.15
     person
    0.15
    /host
    0.14
     countries
    0.14
     location
    0.13
     parties
    0.13
     offending
    0.13
     entity
    0.13
    /target
    0.13
    Activations Density 1.633%

    No Known Activations