© 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. 26928
    Prev
    Next
    INDEX
    Explanations

    a/an/in/on/at + noun phrase

    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
     couch
    -0.09
     Shay
    -0.08
     Bison
    -0.08
    stdClass
    -0.07
     beings
    -0.07
    odata
    -0.07
     nj
    -0.07
    leon
    -0.07
     fel
    -0.07
    gh
    -0.07
    POSITIVE LOGITS
     trance
    0.13
     sé
    0.12
    rig
    0.11
     underwater
    0.11
    /movie
    0.11
    (By
    0.11
     cue
    0.11
     pilgrimage
    0.11
    byn
    0.11
     Olympics
    0.10
    Activations Density 0.009%

    No Known Activations