© 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. 88658
    Prev
    Next
    INDEX
    Explanations

    a few / select few

    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
     Unused
    -0.12
    unused
    -0.11
     unused
    -0.11
    -unused
    -0.10
    ou
    -0.10
     recuper
    -0.09
    reuse
    -0.09
    572
    -0.09
    rup
    -0.09
    izzie
    -0.09
    POSITIVE LOGITS
     handful
    0.31
     few
    0.29
     select
    0.24
     elite
    0.24
    few
    0.23
     Few
    0.22
    Few
    0.21
     minority
    0.19
     selected
    0.19
     exceptions
    0.18
    Activations Density 0.423%

    No Known Activations