© 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. 49721
    Prev
    Next
    INDEX
    Explanations

    the noun phrase

    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
    neath
    -0.11
    FRING
    -0.11
    /met
    -0.10
    dere
    -0.10
    oriously
    -0.10
    _inds
    -0.10
    pps
    -0.09
    ilit
    -0.09
    gage
    -0.09
    cest
    -0.09
    POSITIVE LOGITS
    holds
    0.09
     day
    0.08
     Turnbull
    0.08
    /~
    0.08
     skips
    0.08
     SKIP
    0.07
    .k
    0.07
    conversation
    0.07
    /o
    0.07
    chk
    0.07
    Activations Density 0.149%

    No Known Activations