© 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. 111970
    Prev
    Next
    INDEX
    Explanations

    sal leads to words like salami, salutary, salient

    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
    andid
    -0.09
     apr
    -0.09
    adian
    -0.08
    ardless
    -0.08
    erd
    -0.08
    645
    -0.07
    ordo
    -0.07
    iron
    -0.07
     Equ
    -0.07
    ÃŃ
    -0.07
    POSITIVE LOGITS
    oons
    0.11
    acious
    0.11
     salv
    0.11
     sal
    0.11
     Beste
    0.11
    yers
    0.11
     salvage
    0.11
     sala
    0.11
    chk
    0.11
    ifo
    0.10
    Activations Density 0.004%

    No Known Activations