© 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. 117084
    Prev
    Next
    INDEX
    Explanations

    full version downloads

    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
     downloadable
    -0.14
    .exports
    -0.11
    ê³
    -0.11
     downloads
    -0.11
    arf
    -0.11
    undi
    -0.10
     downloading
    -0.10
    irie
    -0.10
    _loading
    -0.10
    abilit
    -0.10
    POSITIVE LOGITS
     onto
    0.13
     unzip
    0.10
     Sle
    0.08
     volley
    0.08
    Dia
    0.08
     firing
    0.07
     decom
    0.07
     facing
    0.07
    -awesome
    0.07
     Freem
    0.07
    Activations Density 0.268%

    No Known Activations