© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    and followed by words like restore, impair, bone, fast

    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
     basically
    -0.09
     Likewise
    -0.09
     while
    -0.08
     admittedly
    -0.08
     somehow
    -0.08
     alas
    -0.08
     mattered
    -0.08
     although
    -0.08
     vest
    -0.08
     [...]
    -0.08
    POSITIVE LOGITS
    /or
    0.14
    roi
    0.12
     vice
    0.12
    eus
    0.12
    rost
    0.11
    ixo
    0.11
    nika
    0.11
    oks
    0.11
    ICO
    0.11
    roz
    0.11
    Activations Density 0.033%

    No Known Activations