© 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. 88572
    Prev
    Next
    INDEX
    Explanations

    more than, like, as

    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
    arÃŃa
    -0.09
    .HE
    -0.09
     seedu
    -0.08
    irim
    -0.08
    iba
    -0.08
    _listener
    -0.08
    Manifest
    -0.08
     ((!
    -0.08
    _scheme
    -0.08
    antan
    -0.08
    POSITIVE LOGITS
     coherent
    0.15
     usual
    0.15
     typical
    0.14
     traditional
    0.13
     human
    0.12
     conventional
    0.12
     traditionally
    0.12
     recognizable
    0.12
     proper
    0.12
     menacing
    0.11
    Activations Density 0.143%

    No Known Activations