© 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. 49935
    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
     casts
    -0.14
     casting
    -0.13
     Inspir
    -0.13
    eneg
    -0.12
    sto
    -0.12
     mistr
    -0.11
     Horn
    -0.11
    esch
    -0.11
    prep
    -0.11
    orn
    -0.11
    POSITIVE LOGITS
    .nt
    0.07
     Fred
    0.07
     surrounding
    0.07
    /terms
    0.07
    duk
    0.07
    ruz
    0.07
    ETS
    0.07
     involving
    0.06
     talk
    0.06
     Sanford
    0.06
    Activations Density 0.000%

    No Known Activations