© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    communicate effectively or clearly

    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
    iful
    -0.11
    aval
    -0.10
    crest
    -0.10
     nto
    -0.10
    inan
    -0.10
    /components
    -0.10
     perpetr
    -0.10
     DISTRIBUT
    -0.09
     justo
    -0.09
    erval
    -0.09
    POSITIVE LOGITS
     effectively
    0.16
     openly
    0.13
     clearly
    0.12
     verbally
    0.12
     orally
    0.12
     intent
    0.11
     freely
    0.11
     via
    0.11
     Clearly
    0.11
    _via
    0.11
    Activations Density 0.038%

    No Known Activations