© 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. 27654
    Prev
    Next
    INDEX
    Explanations

    end of sentence followed by new thought

    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
     greetings
    -0.11
     respectfully
    -0.11
     trotz
    -0.10
     Bracket
    -0.10
     tre
    -0.10
     willingly
    -0.10
     dare
    -0.10
    atu
    -0.10
    reo
    -0.10
    andro
    -0.09
    POSITIVE LOGITS
    adero
    0.12
     Fav
    0.10
     specifically
    0.10
     mundane
    0.10
     odd
    0.10
     nons
    0.10
     Laugh
    0.10
     recalling
    0.10
     historically
    0.10
     favourite
    0.10
    Activations Density 0.093%

    No Known Activations