© 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. 47493
    Prev
    Next
    INDEX
    Explanations

    There's no

    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
     attachments
    -0.11
     possibilities
    -0.09
    iste
    -0.09
     there
    -0.09
    Altern
    -0.09
     capabilities
    -0.09
     Associated
    -0.08
     safeguards
    -0.08
     priority
    -0.08
     Attach
    -0.08
    POSITIVE LOGITS
     biochemical
    0.11
     currently
    0.10
     persu
    0.10
     tu
    0.10
    ãģĬ
    0.10
     Generic
    0.10
    eki
    0.10
    /json
    0.10
    Generic
    0.10
     Tu
    0.10
    Activations Density 0.163%

    No Known Activations