© 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. 15465
    Prev
    Next
    INDEX
    Explanations

    Bram

    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
    gue
    -0.12
    eph
    -0.11
    °
    -0.09
    iard
    -0.09
    echa
    -0.09
    ele
    -0.09
    ously
    -0.09
    ee
    -0.08
    ey
    -0.08
    ection
    -0.08
    POSITIVE LOGITS
    ming
    0.15
    blings
    0.15
    irez
    0.14
    assage
    0.14
    bam
    0.14
    ifications
    0.13
    pton
    0.12
    bles
    0.12
    jets
    0.12
    bling
    0.11
    Activations Density 0.085%

    No Known Activations