© 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. 6370
    Prev
    Next
    INDEX
    Explanations

    you cannot

    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
    aben
    -0.12
    bear
    -0.11
    inan
    -0.11
    aber
    -0.11
     Iss
    -0.10
     Singleton
    -0.10
     Dimension
    -0.10
     Hod
    -0.10
    431
    -0.10
     Antique
    -0.10
    POSITIVE LOGITS
     inappropriate
    0.14
     underage
    0.11
     improperly
    0.10
     dew
    0.09
     improper
    0.09
     immature
    0.09
     sensitivity
    0.08
     premature
    0.08
     insecure
    0.08
     uncomfortable
    0.08
    Activations Density 0.011%

    No Known Activations