© 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. 88925
    Prev
    Next
    INDEX
    Explanations

    look is

    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
     positional
    -0.11
     loudly
    -0.09
    enda
    -0.09
    /me
    -0.08
     rhythms
    -0.08
     accordion
    -0.08
     Tick
    -0.08
     rhyth
    -0.08
    itta
    -0.08
    urally
    -0.08
    POSITIVE LOGITS
     priceless
    0.16
    Intensity
    0.15
     intensified
    0.13
     intensity
    0.12
     Directed
    0.12
     fierc
    0.12
     flattering
    0.11
     fleeting
    0.11
     repro
    0.11
     directed
    0.11
    Activations Density 0.019%

    No Known Activations