© 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. 46379
    Prev
    Next
    INDEX
    Explanations

    made component or separately from

    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
     inside
    -0.10
     Rut
    -0.09
     epith
    -0.09
     Bale
    -0.08
     lul
    -0.08
     Guth
    -0.08
     ens
    -0.08
     disastrous
    -0.08
    ìļĶ
    -0.08
     unstoppable
    -0.08
    POSITIVE LOGITS
     separately
    0.18
     itself
    0.17
     separate
    0.13
     seperate
    0.13
     reused
    0.13
     Separate
    0.12
    Separ
    0.11
    contains
    0.10
     nic
    0.10
     containing
    0.10
    Activations Density 0.707%

    No Known Activations