© 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. 26714
    Prev
    Next
    INDEX
    Explanations

    providing tips and guides

    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
    enas
    -0.09
    vos
    -0.09
    ça
    -0.08
     coveted
    -0.08
     uncomfortable
    -0.08
     enriched
    -0.08
     camar
    -0.08
     leng
    -0.08
     revel
    -0.08
    elas
    -0.08
    POSITIVE LOGITS
     outline
    0.19
     outlining
    0.18
     recommend
    0.15
     outlined
    0.15
     outlines
    0.15
     tips
    0.15
     recommending
    0.14
    outline
    0.13
     guide
    0.13
     recommends
    0.13
    Activations Density 0.037%

    No Known Activations