© 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. 33622
    Prev
    Next
    INDEX
    Explanations

    a little

    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
     slightly
    -0.12
     subtly
    -0.10
     gn
    -0.10
     glimps
    -0.09
     somewhat
    -0.09
     briefly
    -0.09
     strides
    -0.09
     tremend
    -0.09
     nag
    -0.09
    ç³»
    -0.08
    POSITIVE LOGITS
     sunshine
    0.11
     adversity
    0.10
     randomness
    0.10
     competition
    0.10
     indis
    0.10
     entertainment
    0.10
     nc
    0.09
     hom
    0.09
     unfinished
    0.09
     downtime
    0.09
    Activations Density 0.024%

    No Known Activations