© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115456
    Prev
    Next
    INDEX
    Explanations

    include specific information

    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
    azon
    -0.11
    aida
    -0.10
     Kem
    -0.10
     âĢº
    -0.10
    ignon
    -0.09
    Nach
    -0.09
     tug
    -0.09
    lis
    -0.09
     trouble
    -0.08
    ima
    -0.08
    POSITIVE LOGITS
     mention
    0.23
     references
    0.19
     mentions
    0.19
     disclaimer
    0.17
     clause
    0.17
    mention
    0.16
     clauses
    0.16
     Mention
    0.15
     mentioning
    0.15
     caveat
    0.14
    Activations Density 0.474%

    No Known Activations