© 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. 111786
    Prev
    Next
    INDEX
    Explanations

    name origin or derivation

    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
    onne
    -0.12
    rowser
    -0.11
     names
    -0.11
     mol
    -0.11
    å§ĵåIJį
    -0.10
     Names
    -0.10
     kettle
    -0.10
    ename
    -0.10
     stocking
    -0.10
     headings
    -0.09
    POSITIVE LOGITS
     inspired
    0.17
     derived
    0.16
     derive
    0.13
     chosen
    0.13
     origins
    0.13
     derives
    0.13
     inspiration
    0.12
     homage
    0.12
     origin
    0.12
     derivation
    0.12
    Activations Density 0.237%

    No Known Activations