© 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. 111828
    Prev
    Next
    INDEX
    Explanations

    when asked questions

    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
     convin
    -0.10
    anas
    -0.10
     incapable
    -0.09
     convincing
    -0.09
     convince
    -0.09
     decom
    -0.09
     disappoint
    -0.09
     concentrated
    -0.09
     rival
    -0.08
     autos
    -0.08
    POSITIVE LOGITS
     interrog
    0.13
     pref
    0.13
     answering
    0.12
     permitted
    0.12
     spoken
    0.12
    /question
    0.11
     Echo
    0.11
     questions
    0.10
     spoke
    0.10
     interrogation
    0.10
    Activations Density 0.046%

    No Known Activations