© 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. 33314
    Prev
    Next
    INDEX
    Explanations

    gathering around

    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
    ób
    -0.12
    lobal
    -0.11
    ASE
    -0.11
     dred
    -0.10
     vag
    -0.10
     acompan
    -0.10
     vamp
    -0.10
    >About
    -0.10
     billions
    -0.10
     stride
    -0.10
    POSITIVE LOGITS
     surrounding
    0.11
     formation
    0.11
     around
    0.09
     closest
    0.09
     radius
    0.09
     transf
    0.09
     circle
    0.09
     excluding
    0.09
     spontaneously
    0.09
    formation
    0.08
    Activations Density 0.058%

    No Known Activations