© 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. 32431
    Prev
    Next
    INDEX
    Explanations

    to share tasks items

    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
    nel
    -0.09
     DU
    -0.08
    DU
    -0.08
    sm
    -0.07
     themselves
    -0.07
     knocked
    -0.07
    icity
    -0.07
     prox
    -0.07
     kn
    -0.07
    du
    -0.07
    POSITIVE LOGITS
    ordion
    0.12
     warped
    0.11
     Helm
    0.11
     Nicht
    0.11
    "';
    0.11
    HORT
    0.11
    -character
    0.10
    -Version
    0.10
    .initState
    0.10
     counterpart
    0.10
    Activations Density 0.004%

    No Known Activations