© 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. 88090
    Prev
    Next
    INDEX
    Explanations

    experienced with

    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
     Hav
    -0.08
     standardized
    -0.07
    iona
    -0.07
     predecessor
    -0.07
    gang
    -0.07
     AMC
    -0.07
     UM
    -0.07
    amin
    -0.07
    ino
    -0.07
     overview
    -0.07
    POSITIVE LOGITS
     themselves
    0.12
    usc
    0.12
     rfl
    0.11
    ën
    0.10
    erais
    0.10
     Positive
    0.10
    ffen
    0.10
     Joi
    0.10
    (dd
    0.10
     Danielle
    0.10
    Activations Density 0.004%

    No Known Activations