© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113242
    Prev
    Next
    INDEX
    Explanations

    ( pictured / watch / read

    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
     ek
    -0.08
     darken
    -0.08
    igo
    -0.07
     ticking
    -0.07
    Liked
    -0.07
     hollow
    -0.07
    ito
    -0.07
     chances
    -0.07
     Wide
    -0.07
    yo
    -0.07
    POSITIVE LOGITS
    also
    0.18
     also
    0.18
    whose
    0.17
     see
    0.17
    see
    0.17
    pictured
    0.16
     whose
    0.16
    which
    0.16
    formerly
    0.15
     which
    0.15
    Activations Density 1.099%

    No Known Activations