© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6208
    Prev
    Next
    INDEX
    Explanations

    FC LINGUE

    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
     Voldemort
    -0.09
    Ä°
    -0.09
    eya
    -0.09
    ACHI
    -0.09
     HelloWorld
    -0.09
    (problem
    -0.09
     GetById
    -0.09
     Coronavirus
    -0.09
     Parcelable
    -0.09
     deceased
    -0.09
    POSITIVE LOGITS
     dojo
    0.06
     HANDLE
    0.06
     Helper
    0.06
     masturbating
    0.06
    Middleware
    0.06
     helper
    0.06
     journalistic
    0.05
    oload
    0.05
    ippers
    0.05
     Staff
    0.05
    Activations Density 5.533%

    No Known Activations