© 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. 89458
    Prev
    Next
    INDEX
    Explanations

    under the

    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
     Dal
    -0.10
    cil
    -0.10
    .asp
    -0.09
    atl
    -0.09
    sky
    -0.09
     unm
    -0.09
    aland
    -0.08
    decl
    -0.08
     bodies
    -0.08
    omed
    -0.08
    POSITIVE LOGITS
    neath
    0.11
    essen
    0.10
     Jennings
    0.10
     advoc
    0.09
     notoriously
    0.09
     Cha
    0.09
    sembl
    0.09
     provoc
    0.09
     EITHER
    0.09
    nage
    0.09
    Activations Density 0.009%

    No Known Activations