© 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. 89338
    Prev
    Next
    INDEX
    Explanations

    brand names and extensions

    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
    /qu
    -0.08
    quir
    -0.07
    UIT
    -0.07
     Mayer
    -0.07
    acho
    -0.07
     fragile
    -0.07
    vens
    -0.07
     Gus
    -0.07
    _suite
    -0.06
    hip
    -0.06
    POSITIVE LOGITS
    ishing
    0.21
    enburg
    0.21
    -new
    0.19
    -name
    0.18
    ished
    0.17
    ejs
    0.17
    ishes
    0.16
    steder
    0.16
     spanking
    0.15
     ambassador
    0.15
    Activations Density 0.031%

    No Known Activations