© 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. 88345
    Prev
    Next
    INDEX
    Explanations

    possessive noun modifier

    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
    -même
    -0.13
    /we
    -0.12
    ’d
    -0.12
    /us
    -0.11
    /he
    -0.11
    zzo
    -0.10
    /manage
    -0.09
     someone
    -0.09
     the
    -0.09
    ’re
    -0.09
    POSITIVE LOGITS
    '
    0.20
    ’
    0.16
     behalf
    0.12
    ÂĢÂĻ
    0.12
     insistence
    0.12
     own
    0.12
     finest
    0.11
     biggest
    0.11
    HIP
    0.11
     whereabouts
    0.10
    Activations Density 0.261%

    No Known Activations