© 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. 26034
    Prev
    Next
    INDEX
    Explanations

    academic examination

    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
     brow
    -0.09
     reopening
    -0.09
     belle
    -0.08
     announc
    -0.08
     bows
    -0.08
     recharge
    -0.08
     cock
    -0.08
     conced
    -0.08
     ambit
    -0.08
     fundament
    -0.08
    POSITIVE LOGITS
     rigorous
    0.21
     stringent
    0.20
     extensive
    0.19
     interviews
    0.19
     undergo
    0.19
     scrutiny
    0.18
     interview
    0.18
     strict
    0.17
     vet
    0.17
     scrutin
    0.15
    Activations Density 0.203%

    No Known Activations