© 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. 90228
    Prev
    Next
    INDEX
    Explanations

    how to ask questions

    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
    /how
    -0.08
    igar
    -0.08
    رÙĪ
    -0.08
    -if
    -0.08
    erable
    -0.07
     Wo
    -0.07
     lav
    -0.07
    gether
    -0.07
     enc
    -0.07
    /in
    -0.07
    POSITIVE LOGITS
     about
    0.20
     About
    0.14
    about
    0.14
    ells
    0.14
    ell
    0.13
     ABOUT
    0.13
    dy
    0.13
     ironic
    0.12
    arth
    0.12
     fitting
    0.12
    Activations Density 0.062%

    No Known Activations