© 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. 27062
    Prev
    Next
    INDEX
    Explanations

    was/am getting

    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
     snapping
    -0.09
     altern
    -0.08
    eln
    -0.08
     Pie
    -0.08
     snag
    -0.08
     Cabr
    -0.08
     Baxter
    -0.08
    arih
    -0.07
     Gra
    -0.07
     fo
    -0.07
    POSITIVE LOGITS
     anyhow
    0.17
     anyways
    0.16
     anyway
    0.13
     preca
    0.12
     skeptic
    0.12
     TRACE
    0.12
     habitual
    0.11
     defence
    0.11
     shred
    0.11
     facing
    0.11
    Activations Density 0.197%

    No Known Activations