© 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. 6561
    Prev
    Next
    INDEX
    Explanations

    years duration

    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
    ocos
    -0.10
    afari
    -0.09
     Preconditions
    -0.09
     cog
    -0.09
     Jog
    -0.08
     repl
    -0.08
     hel
    -0.08
     impedance
    -0.08
     asses
    -0.08
     refere
    -0.08
    POSITIVE LOGITS
    thal
    0.11
    aire
    0.10
    ury
    0.10
     myst
    0.10
    otes
    0.10
    Convertible
    0.10
     suspense
    0.09
     Pearl
    0.09
     nails
    0.09
     Eaton
    0.09
    Activations Density 0.001%

    No Known Activations