© 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. 91664
    Prev
    Next
    INDEX
    Explanations

    sending things or people somewhere

    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
     overseas
    -0.09
    oir
    -0.08
    inia
    -0.08
    ossa
    -0.08
    outers
    -0.08
    aker
    -0.07
     carry
    -0.07
     sic
    -0.07
    ни
    -0.07
    week
    -0.07
    POSITIVE LOGITS
     casc
    0.14
     tendr
    0.13
     torrents
    0.13
     sparks
    0.13
     shadows
    0.13
     chill
    0.12
     streams
    0.12
     impulses
    0.12
     portions
    0.12
     spikes
    0.12
    Activations Density 0.006%

    No Known Activations