© 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. 50188
    Prev
    Next
    INDEX
    Explanations

    moving away from

    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
     Dann
    -0.11
    AMI
    -0.10
     cris
    -0.09
     burge
    -0.09
     Mam
    -0.09
     Enum
    -0.09
    DN
    -0.09
    bud
    -0.09
     Hollow
    -0.09
    _mem
    -0.08
    POSITIVE LOGITS
     altogether
    0.20
    alto
    0.18
     preferring
    0.17
     replaced
    0.15
     opting
    0.15
     favor
    0.14
     Alto
    0.13
     favour
    0.13
     focus
    0.12
    focus
    0.12
    Activations Density 0.394%

    No Known Activations