© 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. 49072
    Prev
    Next
    INDEX
    Explanations

    you require verbs

    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
    alic
    -0.10
     Lind
    -0.10
    pret
    -0.10
     preferably
    -0.09
     pret
    -0.09
    ita
    -0.09
     Fot
    -0.09
     apologies
    -0.09
    IfNeeded
    -0.08
     RCC
    -0.08
    POSITIVE LOGITS
     decide
    0.36
     decides
    0.32
     decided
    0.31
     choose
    0.28
     deciding
    0.27
     chooses
    0.27
     chose
    0.26
     chosen
    0.25
     elect
    0.24
     Decide
    0.24
    Activations Density 0.109%

    No Known Activations