© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    original / previous / prior states

    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
     Esper
    -0.11
    eler
    -0.10
    ilm
    -0.09
    inel
    -0.09
     reb
    -0.09
     Reb
    -0.09
     }č↵č↵č↵č↵
    -0.08
     fas
    -0.08
     hic
    -0.08
     Msg
    -0.08
    POSITIVE LOGITS
     previous
    0.21
     original
    0.17
     old
    0.17
    original
    0.16
    previous
    0.16
     pre
    0.15
     former
    0.15
    Previous
    0.15
    old
    0.15
     prior
    0.14
    Activations Density 0.264%

    No Known Activations