© 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. 91620
    Prev
    Next
    INDEX
    Explanations

    meaning and interpretation

    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
     Robotics
    -0.09
    oga
    -0.09
    rh
    -0.09
     Gron
    -0.09
     Funding
    -0.09
    ordo
    -0.09
     doub
    -0.09
     maximizing
    -0.09
    illos
    -0.08
    imbus
    -0.08
    POSITIVE LOGITS
     symbolism
    0.38
     interpretations
    0.36
     Interpret
    0.35
     interpretation
    0.35
     Symbol
    0.34
     symbol
    0.33
     interpreted
    0.32
     interpret
    0.32
     symbolic
    0.31
     meanings
    0.31
    Activations Density 0.239%

    No Known Activations