© 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. 26585
    Prev
    Next
    INDEX
    Explanations

    exchange and communication

    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
     your
    -0.09
     Barr
    -0.08
     yourself
    -0.08
     ASAP
    -0.08
    FT
    -0.08
    alion
    -0.08
     every
    -0.08
    metro
    -0.07
     âĿ
    -0.07
     IMM
    -0.07
    POSITIVE LOGITS
     themselves
    0.13
     collectively
    0.13
     together
    0.13
     mutually
    0.13
    iert
    0.13
     voluntarily
    0.13
     consum
    0.13
     others
    0.12
     prospective
    0.12
    others
    0.12
    Activations Density 0.016%

    No Known Activations