© 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. 111961
    Prev
    Next
    INDEX
    Explanations

    I, we, he, We; seek, live, offer, have

    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
     kindly
    -0.11
     popping
    -0.10
    'on
    -0.10
     definitely
    -0.09
    ENCE
    -0.09
     isn
    -0.09
    lip
    -0.09
     sucker
    -0.09
     decided
    -0.09
    ence
    -0.09
    POSITIVE LOGITS
     seek
    0.16
     seeks
    0.14
     shall
    0.14
     sought
    0.14
     tread
    0.14
     must
    0.12
     hath
    0.12
     cannot
    0.11
     Seek
    0.11
     stand
    0.11
    Activations Density 0.100%

    No Known Activations