© 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. 48413
    Prev
    Next
    INDEX
    Explanations

    trait or trail 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
    aign
    -0.12
    ickt
    -0.11
    å¾ħ
    -0.11
     Truly
    -0.11
    prob
    -0.11
    ToFront
    -0.11
    _OT
    -0.10
    sj
    -0.10
    oir
    -0.10
     plage
    -0.10
    POSITIVE LOGITS
    unes
    0.09
    liner
    0.08
     Blazers
    0.08
    ripper
    0.08
    onta
    0.08
    ers
    0.08
    onte
    0.07
     Puppy
    0.07
    zos
    0.07
    ings
    0.07
    Activations Density 0.022%

    No Known Activations