© 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. 46471
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    2
    -0.10
     gre
    -0.09
     nonzero
    -0.09
     se
    -0.08
     defend
    -0.07
    atori
    -0.07
     bright
    -0.07
     Somebody
    -0.07
     Gre
    -0.07
     defended
    -0.07
    POSITIVE LOGITS
    emd
    0.13
    andr
    0.12
     assure
    0.11
    andre
    0.11
     Sanford
    0.11
     remind
    0.11
     convey
    0.11
    /stretch
    0.11
    gend
    0.11
     Canc
    0.10
    Activations Density 0.081%

    No Known Activations