© 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. 26507
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation

    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
     fountain
    -0.08
     Mour
    -0.08
    @a
    -0.07
     Eastern
    -0.07
     Moder
    -0.07
    uries
    -0.07
     grate
    -0.07
     unofficial
    -0.07
    ultipart
    -0.07
     provided
    -0.07
    POSITIVE LOGITS
    Configurer
    0.10
    unda
    0.10
     Slee
    0.09
    dee
    0.09
     liners
    0.09
    dynamic
    0.09
     amsterdam
    0.09
     glaring
    0.09
    chten
    0.09
    Rp
    0.09
    Activations Density 0.082%

    No Known Activations