© 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. 49353
    Prev
    Next
    INDEX
    Explanations

    syntax and identifiers

    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
    ODE
    -0.13
     “[
    -0.11
    atat
    -0.11
    OCR
    -0.10
    vak
    -0.10
     Cone
    -0.10
     Cell
    -0.10
    itte
    -0.10
     unnamed
    -0.10
     likes
    -0.10
    POSITIVE LOGITS
     ko
    0.08
     Ou
    0.07
    Tpl
    0.07
     prima
    0.07
     transl
    0.07
     dred
    0.07
     outr
    0.07
     LUA
    0.07
     determin
    0.07
    ë¶
    0.07
    Activations Density 0.032%

    No Known Activations