© 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. 115718
    Prev
    Next
    INDEX
    Explanations

    hopes and dreams (dashed, pinned, wrecked)

    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
     Lore
    -0.11
    raid
    -0.10
     staged
    -0.10
     lore
    -0.10
     demanded
    -0.09
     Ludwig
    -0.09
     imperative
    -0.09
    quis
    -0.09
    jaw
    -0.09
    asca
    -0.09
    POSITIVE LOGITS
     hopes
    0.22
     dashed
    0.17
     pinned
    0.16
     shattered
    0.14
     plans
    0.13
     dreams
    0.13
     extingu
    0.13
     ambitions
    0.13
     vested
    0.12
    plans
    0.12
    Activations Density 0.037%

    No Known Activations