© 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. 114375
    Prev
    Next
    INDEX
    Explanations

    can ask or hope

    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
     Laz
    -0.10
    esch
    -0.09
     div
    -0.09
    ument
    -0.09
     Helm
    -0.08
     Personally
    -0.08
     conf
    -0.08
    tridge
    -0.08
     validity
    -0.08
     Flesh
    -0.08
    POSITIVE LOGITS
     dream
    0.38
     dreaming
    0.35
     dreams
    0.34
    dream
    0.32
     dreamed
    0.31
    Dream
    0.29
     Dream
    0.28
     Dreams
    0.27
     hopes
    0.26
     hope
    0.26
    Activations Density 0.051%

    No Known Activations