© 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. 88616
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oyo
    -0.10
     statist
    -0.08
    angen
    -0.08
    ARB
    -0.08
     Bil
    -0.08
     FACT
    -0.08
    intree
    -0.07
     Rece
    -0.07
    loys
    -0.07
     grievances
    -0.07
    POSITIVE LOGITS
     punct
    0.12
    å®ī
    0.10
     unter
    0.10
     scramble
    0.10
    errer
    0.10
    rug
    0.09
    anke
    0.09
     Deutschland
    0.09
    ibs
    0.09
     scrambled
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.