© 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. 6330
    Prev
    Next
    INDEX
    Explanations

    not realizing that

    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
     vog
    -0.10
     Mes
    -0.08
     acceptable
    -0.08
     Swing
    -0.08
     Hol
    -0.07
    -flow
    -0.07
     Bog
    -0.07
    기
    -0.07
     hol
    -0.07
     mes
    -0.07
    POSITIVE LOGITS
     underlying
    0.13
    bao
    0.12
     depths
    0.12
     truths
    0.12
     extent
    0.11
     realise
    0.11
     depth
    0.11
     behind
    0.11
    -depth
    0.11
    Behind
    0.11
    Activations Density 0.042%

    No Known Activations