© 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. 29876
    Prev
    Next
    INDEX
    Explanations

    It followed by verbs like is/was/has/absorbs

    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
     weren
    -0.11
    ees
    -0.11
     already
    -0.11
     Parm
    -0.10
     definitely
    -0.10
     reminds
    -0.10
     surely
    -0.10
    already
    -0.10
     wants
    -0.10
     put
    -0.09
    POSITIVE LOGITS
     consist
    0.12
     notably
    0.11
    alic
    0.11
    asca
    0.10
     consists
    0.10
     aids
    0.10
     typically
    0.10
     thus
    0.10
     can
    0.09
     also
    0.09
    Activations Density 0.698%

    No Known Activations