© 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. 92171
    Prev
    Next
    INDEX
    Explanations

    license or permission to

    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
     topping
    -0.09
     nightmare
    -0.09
     rece
    -0.09
    ugen
    -0.09
     XXX
    -0.09
    gender
    -0.08
     expiry
    -0.08
     sexist
    -0.08
     Rape
    -0.08
     scre
    -0.08
    POSITIVE LOGITS
     indoors
    0.12
     Indoor
    0.11
     indoor
    0.11
     coolest
    0.10
     filmer
    0.10
     Vocabulary
    0.10
     retirees
    0.10
     plaza
    0.10
    verb
    0.09
     nouns
    0.09
    Activations Density 0.161%

    No Known Activations