© 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. 7626
    Prev
    Next
    INDEX
    Explanations

    asking questions, seeking answers

    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
    QT
    -0.09
    Intermediate
    -0.09
    .si
    -0.09
    åĶ
    -0.08
    IFn
    -0.08
     Robertson
    -0.08
    AtA
    -0.08
     Pruitt
    -0.08
    Demon
    -0.08
    ил
    -0.08
    POSITIVE LOGITS
     answer
    0.19
     answering
    0.15
     ANSW
    0.15
    -answer
    0.15
     answered
    0.15
     Answer
    0.14
    answer
    0.13
     unanswered
    0.13
     dod
    0.13
     оÑĤвеÑĤ
    0.13
    Activations Density 0.064%

    No Known Activations