© 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. 31168
    Prev
    Next
    INDEX
    Explanations

    some [noun/adjective phrase]

    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
    yer
    -0.09
     Forms
    -0.08
     fist
    -0.07
     our
    -0.07
    arte
    -0.07
    lon
    -0.07
    ify
    -0.07
     swath
    -0.07
     nearer
    -0.07
     exped
    -0.06
    POSITIVE LOGITS
     strange
    0.15
     irgend
    0.15
     Strange
    0.13
     weird
    0.13
    hest
    0.13
     sort
    0.13
     somehow
    0.12
    Strange
    0.11
     qualche
    0.11
    (ph
    0.11
    Activations Density 0.029%

    No Known Activations