© 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. 33382
    Prev
    Next
    INDEX
    Explanations

    six or sixteen

    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
     dep
    -0.10
     Welch
    -0.10
     Hast
    -0.08
     forb
    -0.08
    ridge
    -0.08
    orial
    -0.08
    egan
    -0.08
     discour
    -0.08
     handicap
    -0.08
     incom
    -0.08
    POSITIVE LOGITS
    teenth
    0.22
    teen
    0.20
    ties
    0.20
    .moves
    0.17
    ty
    0.16
     Sigma
    0.15
    sense
    0.14
    six
    0.13
     Shooter
    0.13
    /se
    0.13
    Activations Density 0.230%

    No Known Activations