© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 29022
    Prev
    Next
    INDEX
    Explanations

    word endings and roots

    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
    ocado
    -0.11
     Lust
    -0.11
    urity
    -0.11
    (er
    -0.10
    mun
    -0.10
     reap
    -0.10
    ToOne
    -0.10
    rop
    -0.10
    cairo
    -0.10
    book
    -0.09
    POSITIVE LOGITS
     secret
    0.10
    ADM
    0.09
    uco
    0.09
     retract
    0.08
    ubic
    0.08
     complex
    0.08
    ului
    0.08
     entire
    0.08
    AMPL
    0.08
     spr
    0.08
    Activations Density 0.013%

    No Known Activations