© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    mand prefix

    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
    zer
    -0.07
    ieran
    -0.07
    nell
    -0.07
     neon
    -0.07
     triangular
    -0.07
     Empire
    -0.07
     SMART
    -0.07
    unix
    -0.07
    unt
    -0.07
     concurrent
    -0.07
    POSITIVE LOGITS
     sheer
    0.13
    yc
    0.12
    elper
    0.11
     aspir
    0.11
    conj
    0.11
     obstruct
    0.10
     Urs
    0.10
    olini
    0.10
     Rosen
    0.10
    hib
    0.10
    Activations Density 0.013%

    No Known Activations