© 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. 25663
    Prev
    Next
    INDEX
    Explanations

    code and configurations

    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
     agr
    -0.10
     Hess
    -0.10
     aggregation
    -0.10
    åĨ
    -0.10
    lw
    -0.09
     Ont
    -0.09
     Obl
    -0.09
    /from
    -0.09
     langu
    -0.09
     Fighting
    -0.09
    POSITIVE LOGITS
    Apart
    0.13
    While
    0.12
    Although
    0.11
     apart
    0.11
    Another
    0.11
    Besides
    0.11
     while
    0.11
     Apart
    0.10
     perv
    0.10
     although
    0.09
    Activations Density 0.004%

    No Known Activations