© 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. 88392
    Prev
    Next
    INDEX
    Explanations

    this . this

    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
    ending
    -0.10
    emann
    -0.10
    -largest
    -0.09
    BU
    -0.09
    eller
    -0.09
     Mend
    -0.09
     bro
    -0.09
    enden
    -0.09
    261
    -0.09
     mend
    -0.09
    POSITIVE LOGITS
    chaft
    0.08
     Frid
    0.08
    thes
    0.08
     ReSharper
    0.07
    istes
    0.07
     Magn
    0.07
    ses
    0.07
     Barbar
    0.07
    -react
    0.07
    asaki
    0.07
    Activations Density 0.281%

    No Known Activations