© 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. 33476
    Prev
    Next
    INDEX
    Explanations

    pulled within, off, up, together, from, for

    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
    lad
    -0.09
     elastic
    -0.08
     eng
    -0.08
     Ant
    -0.07
     invalid
    -0.07
     unread
    -0.07
    .force
    -0.07
     progn
    -0.07
     caus
    -0.07
     shout
    -0.07
    POSITIVE LOGITS
     Werk
    0.12
     starring
    0.11
     gloves
    0.11
     bumper
    0.11
     Ding
    0.11
    umas
    0.10
    ulan
    0.10
     goggles
    0.10
    <quote
    0.10
    ↵				↵
    0.10
    Activations Density 0.033%

    No Known Activations