© 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. 25847
    Prev
    Next
    INDEX
    Explanations

    lisk account, POS, unlock accounts, NANOFLANN, Lodge

    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
     bitcoin
    -0.20
     Bitcoin
    -0.18
     bitcoins
    -0.17
    Bitcoin
    -0.16
     Bitcoins
    -0.13
    bitcoin
    -0.12
     crypto
    -0.12
    crypto
    -0.12
     btc
    -0.11
    /crypto
    -0.11
    POSITIVE LOGITS
     Literature
    0.11
     rewarding
    0.10
    Memo
    0.10
     contract
    0.10
     literary
    0.10
     canine
    0.10
     Mast
    0.09
     epidemi
    0.09
     delegated
    0.09
     abdom
    0.09
    Activations Density 0.063%

    No Known Activations