© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 47567
    Prev
    Next
    INDEX
    Explanations

    click here

    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
     frag
    -0.09
     gab
    -0.08
     Jain
    -0.08
     Andrea
    -0.08
    bare
    -0.08
     lately
    -0.08
     Mich
    -0.08
     scratch
    -0.08
     misc
    -0.08
    ëĤ
    -0.07
    POSITIVE LOGITS
     here
    0.41
    here
    0.34
     HERE
    0.32
     Here
    0.32
     THIS
    0.32
    Here
    0.30
    HERE
    0.27
     THESE
    0.27
    _here
    0.26
    this
    0.25
    Activations Density 0.929%

    No Known Activations