© 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. 117206
    Prev
    Next
    INDEX
    Explanations

    feel the

    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
    —if
    -0.10
     BaÅŁ
    -0.10
    dda
    -0.09
     presumably
    -0.09
     seemed
    -0.09
    han
    -0.09
    —even
    -0.08
    olu
    -0.08
    oha
    -0.08
     verg
    -0.08
    POSITIVE LOGITS
     Prelude
    0.12
    elin
    0.10
    stasy
    0.10
     anticipating
    0.10
    pra
    0.10
     independ
    0.10
     wanna
    0.10
     Depth
    0.10
     hesitant
    0.10
    /I
    0.10
    Activations Density 0.107%

    No Known Activations