© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113830
    Prev
    Next
    INDEX
    Explanations

    operating with purpose

    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
     onsite
    -0.10
    BOT
    -0.09
    God
    -0.09
    enberg
    -0.08
    rot
    -0.08
    lem
    -0.08
    olle
    -0.08
    lick
    -0.08
     Glam
    -0.08
    件
    -0.07
    POSITIVE LOGITS
    fir
    0.11
    ake
    0.11
    ivan
    0.10
     horr
    0.10
    asure
    0.10
     coron
    0.10
     founders
    0.10
    LY
    0.10
     intro
    0.09
    ayah
    0.09
    Activations Density 0.004%

    No Known Activations