© 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. 49077
    Prev
    Next
    INDEX
    Explanations

    names followed by profession or country

    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
     uncert
    -0.11
     Cena
    -0.10
    erin
    -0.10
     Dut
    -0.10
     Elli
    -0.10
    @update
    -0.10
     Jeg
    -0.10
    ieber
    -0.10
     Ack
    -0.10
    #aa
    -0.10
    POSITIVE LOGITS
    660
    0.08
    Opts
    0.07
    igu
    0.07
    gee
    0.07
    onga
    0.07
    Invariant
    0.07
    GV
    0.06
     Euro
    0.06
     Bundes
    0.06
    ère
    0.06
    Activations Density 0.130%

    No Known Activations