© 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. 32247
    Prev
    Next
    INDEX
    Explanations

    deep followed by a noun

    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
    actic
    -0.10
    illes
    -0.09
     mildly
    -0.09
    ive
    -0.09
    aro
    -0.09
    еж
    -0.09
    edy
    -0.09
    oday
    -0.08
     AVG
    -0.08
    uz
    -0.08
    POSITIVE LOGITS
    ening
    0.27
    ened
    0.23
    -root
    0.20
     seated
    0.19
    (er
    0.18
    -reaching
    0.14
    fake
    0.13
    eners
    0.13
    thro
    0.13
     dive
    0.13
    Activations Density 0.061%

    No Known Activations