© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48593
    Prev
    Next
    INDEX
    Explanations

    interconnecting or intermixed

    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
    orgen
    -0.09
     Came
    -0.08
    ophobic
    -0.08
    riz
    -0.08
     arrog
    -0.07
    «
    -0.07
     Heard
    -0.07
     «
    -0.07
     utilization
    -0.07
     phys
    -0.07
    POSITIVE LOGITS
    mesh
    0.15
    ming
    0.14
     intertwined
    0.14
    mixed
    0.13
    linked
    0.13
    stitial
    0.13
     ming
    0.13
     woven
    0.12
    locked
    0.12
    mix
    0.12
    Activations Density 0.017%

    No Known Activations