© 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. 16825
    Prev
    Next
    INDEX
    Explanations

    it is / it's

    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
     Mag
    -0.10
     Collapse
    -0.09
     fr
    -0.09
     mag
    -0.09
     fri
    -0.09
     rendered
    -0.09
     parti
    -0.09
     ad
    -0.08
    ales
    -0.08
     Blades
    -0.08
    POSITIVE LOGITS
     existed
    0.12
     eb
    0.11
     evolved
    0.11
     corro
    0.11
     Gur
    0.11
     REPRESENT
    0.11
     ALWAYS
    0.11
     transc
    0.11
     Ev
    0.10
     perv
    0.10
    Activations Density 0.109%

    No Known Activations