© 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. 91044
    Prev
    Next
    INDEX
    Explanations

    070 shake, 036 size, 048 38

    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
     undo
    -0.09
     Downing
    -0.08
    leh
    -0.08
     Schro
    -0.08
    amac
    -0.08
    amu
    -0.08
    ij
    -0.07
     munch
    -0.07
    _recovery
    -0.07
     cent
    -0.07
    POSITIVE LOGITS
     Venez
    0.10
    ces
    0.10
    esso
    0.09
    sic
    0.09
    nic
    0.09
    ieres
    0.09
    scape
    0.09
    indle
    0.09
    sb
    0.09
     tir
    0.09
    Activations Density 0.039%

    No Known Activations