© 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. 112519
    Prev
    Next
    INDEX
    Explanations

    copyright notice license file

    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
     hem
    -0.09
    Naz
    -0.08
    ione
    -0.08
     Bordeaux
    -0.08
     McK
    -0.07
     Trev
    -0.07
    Aura
    -0.07
     shadow
    -0.07
    ION
    -0.07
    okus
    -0.07
    POSITIVE LOGITS
     Orig
    0.12
    pector
    0.11
     metam
    0.10
     Vocal
    0.10
    /mail
    0.10
     Norm
    0.10
    ellan
    0.10
    atron
    0.10
    astro
    0.10
    panic
    0.10
    Activations Density 1.327%

    No Known Activations