© 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. 50430
    Prev
    Next
    INDEX
    Explanations

    pseudo- prefix

    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
     Hind
    -0.08
    tons
    -0.08
     indu
    -0.08
     Staples
    -0.08
    icol
    -0.08
     cal
    -0.08
     Kal
    -0.08
    itational
    -0.08
     descriptors
    -0.08
     dissert
    -0.07
    POSITIVE LOGITS
    onym
    0.14
     pseud
    0.14
    ocode
    0.12
    oras
    0.12
     invers
    0.12
    onyms
    0.12
     pseudo
    0.11
    onymous
    0.11
    alles
    0.10
     badly
    0.10
    Activations Density 0.026%

    No Known Activations