© 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. 7262
    Prev
    Next
    INDEX
    Explanations

    receive or send

    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
     perf
    -0.06
     conscience
    -0.06
     fatt
    -0.06
     Bull
    -0.06
    ress
    -0.06
     Span
    -0.06
     Mint
    -0.06
     Str
    -0.06
    dess
    -0.05
     Spa
    -0.05
    POSITIVE LOGITS
     receiving
    0.18
     receipt
    0.16
     Pence
    0.15
     RECE
    0.14
     receivers
    0.14
     receptions
    0.14
     Rece
    0.13
     received
    0.13
    receive
    0.13
     receives
    0.13
    Activations Density 0.195%

    No Known Activations