© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114596
    Prev
    Next
    INDEX
    Explanations

    phrasing a possibility

    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
    aza
    -0.11
    Ìģ
    -0.11
    town
    -0.10
    /out
    -0.10
    trap
    -0.10
    tics
    -0.10
    ething
    -0.10
    tement
    -0.09
     possibly
    -0.09
    thon
    -0.09
    POSITIVE LOGITS
     unsur
    0.11
    med
    0.11
    ably
    0.10
     there
    0.10
    iry
    0.10
    sti
    0.09
    sst
    0.09
     surprisingly
    0.09
    forth
    0.09
    st
    0.09
    Activations Density 0.028%

    No Known Activations