© 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. 15282
    Prev
    Next
    INDEX
    Explanations

    suspension systems and components

    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
     nond
    -0.12
     masc
    -0.10
    zzo
    -0.10
     Jug
    -0.10
     bom
    -0.10
    estar
    -0.10
    DO
    -0.10
    umni
    -0.09
    isy
    -0.09
    acker
    -0.09
    POSITIVE LOGITS
     Kami
    0.09
     hosting
    0.08
     Suzuki
    0.08
     Dickinson
    0.08
     Lopez
    0.08
     Clintons
    0.08
     lifted
    0.08
     caval
    0.07
     withheld
    0.07
     riding
    0.07
    Activations Density 0.005%

    No Known Activations