© 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. 29252
    Prev
    Next
    INDEX
    Explanations

    season dates

    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
     hyp
    -0.07
     Freem
    -0.07
     hypert
    -0.06
     inf
    -0.06
     Quint
    -0.06
    iliar
    -0.06
     stead
    -0.06
    ervation
    -0.06
    enet
    -0.06
    aset
    -0.05
    POSITIVE LOGITS
    201
    0.23
    202
    0.20
    ongo
    0.19
     present
    0.18
    present
    0.18
    -present
    0.17
    Present
    0.17
     ongoing
    0.17
     Present
    0.17
     presently
    0.15
    Activations Density 0.381%

    No Known Activations