© 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. 50011
    Prev
    Next
    INDEX
    Explanations

    "this" followed by web or file terms

    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
     lump
    -0.11
     Wah
    -0.10
    dent
    -0.09
    ffc
    -0.09
     ãĥ»
    -0.09
    Explorer
    -0.09
     Singular
    -0.09
    enci
    -0.09
    oren
    -0.09
    bah
    -0.09
    POSITIVE LOGITS
     flyer
    0.09
     remorse
    0.09
    atat
    0.09
    uja
    0.09
    &C
    0.08
     ($)
    0.08
     Gir
    0.08
    emy
    0.08
     overl
    0.08
    emet
    0.08
    Activations Density 0.774%

    No Known Activations