© 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. 115754
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    390
    -0.11
    HEY
    -0.10
     distinction
    -0.10
    iani
    -0.10
    dden
    -0.10
     distinctions
    -0.10
    /account
    -0.10
     Fle
    -0.09
    atives
    -0.09
     washed
    -0.09
    POSITIVE LOGITS
     sexes
    0.08
     Strange
    0.08
     dots
    0.08
     Establishment
    0.08
    ooter
    0.08
    PAIR
    0.08
     Cause
    0.07
     Kore
    0.07
    itere
    0.07
    али
    0.07
    Activations Density 0.626%

    No Known Activations