© 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. 116136
    Prev
    Next
    INDEX
    Explanations

    MEMORANDUM or MurmurHash

    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
    оваÑĢ
    -0.10
     Klo
    -0.10
    /un
    -0.09
    /bus
    -0.09
    wyn
    -0.09
    arus
    -0.09
    erten
    -0.09
    iator
    -0.09
    urope
    -0.09
     squarely
    -0.09
    POSITIVE LOGITS
    ances
    0.12
    udu
    0.11
    ongs
    0.11
    usto
    0.11
    andom
    0.11
    ously
    0.10
    ansk
    0.10
     softly
    0.09
    RIES
    0.09
     sweet
    0.09
    Activations Density 0.004%

    No Known Activations