© 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. 28508
    Prev
    Next
    INDEX
    Explanations

    acronym abbreviations

    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
    efe
    -0.09
    nowled
    -0.09
    ล
    -0.08
    tek
    -0.08
    plete
    -0.08
    INDER
    -0.08
    @SuppressWarnings
    -0.08
    imat
    -0.08
     proven
    -0.08
     hrs
    -0.07
    POSITIVE LOGITS
    Msp
    0.09
    ,GL
    0.09
     DERP
    0.09
    VF
    0.09
    F
    0.09
    U
    0.09
     cond
    0.09
     Ung
    0.08
     Salvation
    0.08
    -Co
    0.08
    Activations Density 1.215%

    No Known Activations