© 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. 50274
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     apprec
    -0.09
    leo
    -0.08
     PEN
    -0.08
     POS
    -0.08
    erm
    -0.07
     Pen
    -0.07
     pen
    -0.07
     fair
    -0.07
    inger
    -0.07
     dy
    -0.07
    POSITIVE LOGITS
    Datas
    0.11
    оÑģÑĮ
    0.11
    -UA
    0.10
    icit
    0.10
     Curse
    0.10
    pragma
    0.10
    erez
    0.10
    tees
    0.10
    BU
    0.10
    (android
    0.10
    Activations Density 0.000%

    No Known Activations