© 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. 91017
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Harr
    -0.12
    AIM
    -0.10
     tread
    -0.10
     AIM
    -0.09
    awan
    -0.09
    Fu
    -0.09
     Coffee
    -0.08
     survivor
    -0.08
    wan
    -0.08
    bum
    -0.08
    POSITIVE LOGITS
    ansi
    0.08
    odem
    0.08
     aforementioned
    0.08
     Essen
    0.08
     readily
    0.08
     sparkling
    0.08
     Fleming
    0.08
     tun
    0.08
     Ansi
    0.08
    otos
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.