© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
     informed
    -0.09
     insight
    -0.09
     descriptions
    -0.08
     ras
    -0.08
     insights
    -0.08
    apus
    -0.08
     streak
    -0.07
     Guests
    -0.07
    Descri
    -0.07
     character
    -0.07
    POSITIVE LOGITS
     studies
    0.27
     study
    0.25
    study
    0.22
     conducted
    0.22
     trials
    0.20
     Studies
    0.20
     Study
    0.19
     experiments
    0.19
    _study
    0.18
     Conduct
    0.17
    Activations Density 0.711%

    No Known Activations