© 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. 88162
    Prev
    Next
    INDEX
    Explanations

    best practices

    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
    ALLY
    -0.11
    uploaded
    -0.10
    iest
    -0.10
    bare
    -0.09
     finest
    -0.09
    ally
    -0.09
    bern
    -0.09
    acz
    -0.09
     fon
    -0.09
    _ends
    -0.09
    POSITIVE LOGITS
    seller
    0.26
    owing
    0.21
    -selling
    0.21
    -known
    0.19
     suited
    0.19
    -case
    0.19
    -su
    0.18
    ow
    0.18
    owment
    0.17
    ows
    0.17
    Activations Density 0.087%

    No Known Activations