© 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. 27485
    Prev
    Next
    INDEX
    Explanations

    resolution, development, reduction, control, identification

    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
    oble
    -0.12
    ye
    -0.11
    wick
    -0.11
    adro
    -0.11
     Goodman
    -0.11
    Trail
    -0.11
    YE
    -0.11
     Kee
    -0.10
    uye
    -0.10
    .sg
    -0.10
    POSITIVE LOGITS
    íķĺ기
    0.09
    ment
    0.08
    /types
    0.08
     Gir
    0.08
    age
    0.08
    ides
    0.08
    /color
    0.08
     McGr
    0.07
    edException
    0.07
     Fetish
    0.07
    Activations Density 1.772%

    No Known Activations