© 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. 112769
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
     Hearth
    -0.08
     misunder
    -0.08
     sav
    -0.08
     bail
    -0.08
     belly
    -0.08
     ideally
    -0.08
     modal
    -0.08
    oha
    -0.08
     tre
    -0.07
     eventual
    -0.07
    POSITIVE LOGITS
     Pey
    0.11
    Already
    0.10
    Prostit
    0.10
    mun
    0.10
    dv
    0.10
     unst
    0.10
    ussy
    0.09
    737
    0.09
     EXTRA
    0.09
    stre
    0.09
    Activations Density 0.017%

    No Known Activations