© 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. 26204
    Prev
    Next
    INDEX
    Explanations

    single-cell and single-use contexts

    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
    ipp
    -0.11
    nite
    -0.11
    gesch
    -0.10
     Giov
    -0.10
     Preston
    -0.10
    pile
    -0.10
     Pen
    -0.10
     Chandler
    -0.10
    ror
    -0.10
    925
    -0.10
    POSITIVE LOGITS
    /single
    0.27
    (single
    0.17
    -single
    0.15
    tons
    0.12
     isolated
    0.11
    /small
    0.10
    -minded
    0.09
     isolate
    0.09
     survivor
    0.09
     indiv
    0.09
    Activations Density 0.455%

    No Known Activations