© 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. 26798
    Prev
    Next
    INDEX
    Explanations

    Sa followed by word parts

    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
    alla
    -0.09
    Mock
    -0.08
     helt
    -0.08
    /mock
    -0.08
    ض
    -0.08
    izza
    -0.08
     Morton
    -0.08
     worlds
    -0.08
    l
    -0.07
    ÑĢи
    -0.07
    POSITIVE LOGITS
    aved
    0.16
    unders
    0.15
    igon
    0.11
    USAGE
    0.11
    usage
    0.11
    enger
    0.10
     inval
    0.10
    stry
    0.10
    _SIG
    0.10
    unter
    0.10
    Activations Density 0.083%

    No Known Activations