© 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. 47429
    Prev
    Next
    INDEX
    Explanations

    suspicious something

    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
     visibly
    -0.11
     rede
    -0.10
    _ES
    -0.09
    asley
    -0.09
     Rosen
    -0.09
    elsey
    -0.09
    .il
    -0.09
    ë¦Ħ
    -0.09
     encoded
    -0.09
    oller
    -0.09
    POSITIVE LOGITS
     something
    0.11
     Something
    0.10
    á»
    0.10
     obstruction
    0.10
     object
    0.10
     evenly
    0.09
    iras
    0.09
     surfaces
    0.09
    oft
    0.09
    719
    0.09
    Activations Density 0.069%

    No Known Activations