© 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. 26366
    Prev
    Next
    INDEX
    Explanations

    misinterpretation or error

    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
     competit
    -0.08
    aN
    -0.08
     kindly
    -0.08
     Loving
    -0.08
     tangible
    -0.08
    PTS
    -0.08
    unset
    -0.08
     Potter
    -0.08
    onde
    -0.08
    ListOf
    -0.07
    POSITIVE LOGITS
    interpret
    0.15
     interpretation
    0.13
    steps
    0.12
    interpreted
    0.12
     interpreted
    0.12
     understood
    0.12
     interpreting
    0.11
    -under
    0.11
     construed
    0.11
    interpre
    0.11
    Activations Density 0.010%

    No Known Activations