© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    cheap things

    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
    oba
    -0.08
     defer
    -0.08
     Couch
    -0.08
    boarding
    -0.08
     Epic
    -0.07
    364
    -0.07
     Henrik
    -0.07
     deficiencies
    -0.07
    arial
    -0.07
    acht
    -0.07
    POSITIVE LOGITS
    jack
    0.17
    ening
    0.17
    ens
    0.15
     thrill
    0.14
    ened
    0.14
    -shot
    0.13
    shot
    0.13
     dime
    0.12
    stakes
    0.12
    jer
    0.12
    Activations Density 0.002%

    No Known Activations