© 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. 115893
    Prev
    Next
    INDEX
    Explanations

    Is missing

    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
    bd
    -0.09
     starving
    -0.09
    UP
    -0.08
    rox
    -0.08
    161
    -0.08
    ho
    -0.08
    ulum
    -0.08
    ALA
    -0.08
     roadside
    -0.07
     rex
    -0.07
    POSITIVE LOGITS
    istes
    0.14
    afc
    0.12
     Sundays
    0.11
    umbs
    0.10
    igli
    0.10
    zych
    0.10
    arda
    0.10
    lfw
    0.10
     Edition
    0.10
    -cols
    0.10
    Activations Density 0.001%

    No Known Activations