© 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. 115070
    Prev
    Next
    INDEX
    Explanations

    unmatched comparison

    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
    @dynamic
    -0.12
     unusually
    -0.11
    nist
    -0.11
    quo
    -0.11
    nton
    -0.11
    Invariant
    -0.11
    verty
    -0.10
     overriding
    -0.10
    ÙĨ
    -0.10
    _dm
    -0.10
    POSITIVE LOGITS
     unmatched
    0.13
     unparalleled
    0.11
     matched
    0.11
     unbe
    0.10
     anywhere
    0.10
     peer
    0.10
     match
    0.10
     elsewhere
    0.10
     among
    0.10
     elegance
    0.10
    Activations Density 0.032%

    No Known Activations