© 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. 114152
    Prev
    Next
    INDEX
    Explanations

    names and compound words starting with "back"

    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
    ess
    -0.12
    omp
    -0.10
    kins
    -0.10
    rious
    -0.09
    unter
    -0.09
    deb
    -0.09
    boom
    -0.09
     dak
    -0.08
    imir
    -0.08
    eko
    -0.08
    POSITIVE LOGITS
    tracking
    0.18
    slash
    0.18
    logged
    0.17
    wards
    0.16
    seat
    0.16
    ped
    0.15
    stab
    0.15
    ronym
    0.15
    side
    0.15
    gam
    0.15
    Activations Density 0.519%

    No Known Activations