© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48921
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
     dere
    -0.10
    EDA
    -0.10
     ffi
    -0.10
    greg
    -0.09
     MIPS
    -0.09
     flick
    -0.09
     io
    -0.09
     SIMD
    -0.09
     foss
    -0.09
     cannons
    -0.08
    POSITIVE LOGITS
     (.
    0.18
     .
    0.17
     PDF
    0.15
     [.
    0.15
     *.
    0.15
     '*.
    0.14
    (".
    0.14
     extension
    0.14
     ".
    0.14
    rar
    0.14
    Activations Density 0.917%

    No Known Activations