© 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. 47078
    Prev
    Next
    INDEX
    Explanations

    license code

    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
     ing
    -0.08
     Coleman
    -0.08
    orus
    -0.07
     bez
    -0.07
    Cole
    -0.07
     honeymoon
    -0.07
    ampo
    -0.07
     Meer
    -0.07
    adge
    -0.07
    ptron
    -0.07
    POSITIVE LOGITS
     pedest
    0.11
    .library
    0.10
     acidity
    0.10
    273
    0.10
     tall
    0.10
    ì°
    0.10
    prm
    0.10
    _safe
    0.10
    233
    0.10
    entr
    0.10
    Activations Density 0.004%

    No Known Activations