© 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. 89744
    Prev
    Next
    INDEX
    Explanations

    location or file information

    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
    cline
    -0.10
    dek
    -0.10
     Ard
    -0.10
    ToPoint
    -0.10
    hyp
    -0.09
     abre
    -0.09
    bol
    -0.09
     Hust
    -0.09
     selber
    -0.09
     Loc
    -0.09
    POSITIVE LOGITS
     upstairs
    0.38
     downstairs
    0.36
     nearby
    0.25
     elsewhere
    0.18
     somewhere
    0.15
     currently
    0.14
     Nearby
    0.14
     waiting
    0.14
     inside
    0.13
     below
    0.13
    Activations Density 0.216%

    No Known Activations