© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    S. D. /T D B F =S D S D D

    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
    -0.11
    iedo
    -0.09
     angst
    -0.08
    iec
    -0.08
     bureaucr
    -0.08
    )throws
    -0.08
     assort
    -0.08
    irut
    -0.07
     dub
    -0.07
    usra
    -0.07
    POSITIVE LOGITS
    wizard
    0.11
     Sheridan
    0.10
     alleen
    0.10
    ARAM
    0.10
     Interviews
    0.10
    aram
    0.10
     discovery
    0.10
     Cong
    0.10
     Moj
    0.10
    atoi
    0.09
    Activations Density 0.003%

    No Known Activations