© 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. 33026
    Prev
    Next
    INDEX
    Explanations

    compliance with license

    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
     Bes
    -0.10
    ilig
    -0.09
    vers
    -0.09
     Hindered
    -0.09
    bdb
    -0.09
    illac
    -0.09
    _alloc
    -0.09
    (concat
    -0.09
    bes
    -0.09
    icit
    -0.09
    POSITIVE LOGITS
     Oval
    0.09
     arg
    0.09
    une
    0.09
     Crafts
    0.09
     ag
    0.08
    XF
    0.08
     Arg
    0.08
    uft
    0.08
     indoor
    0.08
    oub
    0.08
    Activations Density 0.001%

    No Known Activations