© 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. 112658
    Prev
    Next
    INDEX
    Explanations

    vert and related words

    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
    cco
    -0.12
    arti
    -0.11
    aving
    -0.10
     Impossible
    -0.10
     Wrapper
    -0.09
    atif
    -0.09
    abe
    -0.09
     dare
    -0.09
    ITIES
    -0.09
    therapy
    -0.09
    POSITIVE LOGITS
    eid
    0.09
    igrated
    0.09
    Td
    0.09
    èĬĤ
    0.08
    ikip
    0.08
     overt
    0.08
     wizards
    0.08
    orph
    0.08
     Staples
    0.08
     Humph
    0.08
    Activations Density 0.017%

    No Known Activations