© 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. 28115
    Prev
    Next
    INDEX
    Explanations

    refine, narrow, precise

    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
    avar
    -0.11
     arbitrary
    -0.11
     smear
    -0.11
     Rat
    -0.11
     whit
    -0.10
    zza
    -0.10
     ebenfalls
    -0.10
    afort
    -0.10
     gaz
    -0.10
     rewrite
    -0.10
    POSITIVE LOGITS
     precisely
    0.17
     narrowing
    0.17
     narrow
    0.17
     targeted
    0.17
     narrowly
    0.17
     narrowed
    0.17
     Narrow
    0.17
     precise
    0.16
     tailored
    0.15
     tailor
    0.15
    Activations Density 0.099%

    No Known Activations