© 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. 115806
    Prev
    Next
    INDEX
    Explanations

    "Dear", "Hello", "valued"

    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
    VEC
    -0.12
     races
    -0.11
     Raleigh
    -0.10
     ming
    -0.10
    mk
    -0.10
     outfield
    -0.10
     Michel
    -0.09
     Races
    -0.09
    uard
    -0.09
    oler
    -0.09
    POSITIVE LOGITS
     valued
    0.10
    esco
    0.10
    reb
    0.09
    aco
    0.09
    SKU
    0.08
    wagon
    0.08
     scape
    0.08
    IPA
    0.08
     CDDL
    0.08
     Warren
    0.08
    Activations Density 0.001%

    No Known Activations