© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    special characters and abbreviations

    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
    noinspection
    -0.11
     (...)
    -0.11
    "."
    -0.11
     â
    -0.10
    .""
    -0.10
    zin
    -0.10
     [...]
    -0.09
     "...
    -0.09
    ...'
    -0.09
    ...</
    -0.09
    POSITIVE LOGITS
    Âł
    0.49
    Âł↵
    0.39
    ³³
    0.31
    ³³³
    0.27
     Âł Âł Âł Âł
    0.26
     Âł Âł
    0.26
    ³³³³³³³³
    0.24
     Âł
    0.24
    ³³³³
    0.24
    ³³³³³³³
    0.21
    Activations Density 0.578%

    No Known Activations