© 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. 116347
    Prev
    Next
    INDEX
    Explanations

    long

    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
     impost
    -0.09
    LIN
    -0.08
     lan
    -0.08
    Rent
    -0.08
     Abrams
    -0.08
    vide
    -0.07
     length
    -0.07
     contingency
    -0.07
     Gall
    -0.07
    lifetime
    -0.07
    POSITIVE LOGITS
    AZE
    0.12
     adj
    0.11
    opc
    0.10
    imi
    0.10
     witnesses
    0.10
    aceous
    0.10
     Witnesses
    0.10
     dó
    0.10
    tas
    0.10
    -Sah
    0.10
    Activations Density 0.110%

    No Known Activations