© 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. 46626
    Prev
    Next
    INDEX
    Explanations

    in case you haven't

    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
     ost
    -0.12
    apan
    -0.11
     Continental
    -0.10
     UPC
    -0.09
     continental
    -0.09
     Aware
    -0.08
    ober
    -0.08
     admitted
    -0.07
    ripp
    -0.07
    icum
    -0.07
    POSITIVE LOGITS
     wondering
    0.25
     wondered
    0.23
     hadn
    0.22
     forgot
    0.18
     wonder
    0.18
     doubted
    0.17
     didn
    0.17
    Didn
    0.16
     Wonder
    0.16
     confused
    0.15
    Activations Density 0.056%

    No Known Activations