© 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. 50035
    Prev
    Next
    INDEX
    Explanations

    technical synthesis or thesis

    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
     VOC
    -0.09
    ÂĢÂĻ
    -0.09
    oman
    -0.09
    belie
    -0.09
     frags
    -0.09
    ".↵↵↵↵
    -0.09
    illy
    -0.09
    /**<
    -0.09
    onda
    -0.09
    trap
    -0.08
    POSITIVE LOGITS
     trif
    0.09
    >čč↵
    0.09
     hosp
    0.08
     anzeigen
    0.08
     lucky
    0.08
     Narrow
    0.08
     sheets
    0.08
     narrow
    0.08
     minors
    0.08
     immedi
    0.08
    Activations Density 0.047%

    No Known Activations