© 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. 88781
    Prev
    Next
    INDEX
    Explanations

    right/wrong followed by place/direction/time

    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
     appropriate
    -0.09
     proper
    -0.09
     pertinent
    -0.08
     Valle
    -0.08
     necessary
    -0.08
     positioning
    -0.08
    ÂŃ
    -0.08
    awk
    -0.07
     quotient
    -0.07
    aise
    -0.07
    POSITIVE LOGITS
     place
    0.20
     PLACE
    0.13
    place
    0.13
     Place
    0.12
     destination
    0.12
    Place
    0.11
     site
    0.11
     website
    0.11
     blog
    0.11
    yal
    0.10
    Activations Density 0.004%

    No Known Activations