© 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. 31760
    Prev
    Next
    INDEX
    Explanations

    verbs followed by destinations or purposes

    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
     Forbes
    -0.10
     Wag
    -0.10
     Bene
    -0.10
     Buff
    -0.10
     simult
    -0.10
     meanwhile
    -0.09
    usat
    -0.09
    /channel
    -0.09
    uffix
    -0.09
     Ka
    -0.09
    POSITIVE LOGITS
    rijk
    0.09
    immel
    0.09
    ham
    0.09
     allot
    0.09
     Freeman
    0.08
    omorphic
    0.08
    çķª
    0.08
    mach
    0.08
    oken
    0.08
    ode
    0.08
    Activations Density 0.264%

    No Known Activations