© 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. 47421
    Prev
    Next
    INDEX
    Explanations

    united states cases

    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
     Featured
    -0.10
    /by
    -0.09
    indent
    -0.09
    illus
    -0.09
     vale
    -0.09
    atype
    -0.09
     spectro
    -0.09
    akest
    -0.09
    abstract
    -0.09
    ptype
    -0.09
    POSITIVE LOGITS
    gi
    0.10
     lawful
    0.09
     Yao
    0.09
     spike
    0.08
    оÑĤоÑĢ
    0.08
     Hubb
    0.08
    (or
    0.08
     ven
    0.08
    elda
    0.08
    rine
    0.07
    Activations Density 0.002%

    No Known Activations