© 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. 16452
    Prev
    Next
    INDEX
    Explanations

    come to light/pass/fruition/bear

    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
     expend
    -0.08
    olib
    -0.08
     wisdom
    -0.08
     backed
    -0.08
    implicit
    -0.07
    osp
    -0.07
     regained
    -0.07
    358
    -0.07
     backups
    -0.07
    wie
    -0.07
    POSITIVE LOGITS
     fruition
    0.23
     prominence
    0.15
     fore
    0.14
    zug
    0.13
     mind
    0.13
     forefront
    0.12
    arse
    0.12
     us
    0.12
     blows
    0.12
    passes
    0.12
    Activations Density 0.036%

    No Known Activations