© 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. 33062
    Prev
    Next
    INDEX
    Explanations

    growth, cascade, multiplying

    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
     shuffled
    -0.12
     shuffle
    -0.12
    shuffle
    -0.12
    ::-
    -0.10
     interchange
    -0.10
     tie
    -0.10
     reversed
    -0.09
     phases
    -0.09
    CEE
    -0.09
     sph
    -0.09
    POSITIVE LOGITS
     exponentially
    0.30
     exponential
    0.29
     recursively
    0.25
     casc
    0.24
     ampl
    0.23
     doubling
    0.22
     cascade
    0.22
     multiplying
    0.21
     Casc
    0.21
     Cascade
    0.20
    Activations Density 1.323%

    No Known Activations