© 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. 30700
    Prev
    Next
    INDEX
    Explanations

    dates and testing

    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
    ett
    -0.07
     Recently
    -0.07
    ousse
    -0.07
    oui
    -0.07
    umer
    -0.07
    esh
    -0.07
     sober
    -0.07
     recently
    -0.07
    Keith
    -0.07
    aky
    -0.07
    POSITIVE LOGITS
     comps
    0.12
     Orr
    0.12
     Bak
    0.11
     ton
    0.11
     pending
    0.11
     Marion
    0.10
    spath
    0.10
     Buch
    0.10
     centres
    0.10
    /tab
    0.10
    Activations Density 0.015%

    No Known Activations