© 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. 4559
    Prev
    Next
    INDEX
    Explanations

    lists with colons or periods

    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
     ....↵↵
    -0.11
    Fluid
    -0.10
     Kol
    -0.10
     neb
    -0.09
     rem
    -0.09
     nat
    -0.09
    unload
    -0.09
     (--
    -0.09
     Hills
    -0.09
    uber
    -0.09
    POSITIVE LOGITS
    enen
    0.08
     envi
    0.08
    _tra
    0.08
     intens
    0.08
     cred
    0.08
     decency
    0.08
     Episcopal
    0.08
     recon
    0.08
     testify
    0.07
     Lol
    0.07
    Activations Density 0.001%

    No Known Activations