© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27848
    Prev
    Next
    INDEX
    Explanations

    first or last order

    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
     fier
    -0.08
    agi
    -0.08
    scr
    -0.08
     thereafter
    -0.07
     strut
    -0.07
    onth
    -0.07
     Previously
    -0.07
     simult
    -0.07
     stub
    -0.07
    anie
    -0.07
    POSITIVE LOGITS
     two
    0.17
    /current
    0.16
     incarnation
    0.14
     ones
    0.14
    两
    0.13
    two
    0.13
     beiden
    0.11
    cher
    0.11
     Waste
    0.11
     Rud
    0.11
    Activations Density 0.133%

    No Known Activations