© 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. 4613
    Prev
    Next
    INDEX
    Explanations

    called or announced

    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
    лиÑĨ
    -0.10
     resend
    -0.10
    ober
    -0.10
     Getty
    -0.09
    lops
    -0.09
     Baz
    -0.09
    enberg
    -0.09
    utz
    -0.09
     revers
    -0.09
    :Get
    -0.09
    POSITIVE LOGITS
     summons
    0.13
     announce
    0.13
     call
    0.12
     calls
    0.12
     announc
    0.12
     dequeue
    0.11
     callers
    0.11
     called
    0.11
     Calling
    0.11
     summoned
    0.11
    Activations Density 0.104%

    No Known Activations