© 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. 46453
    Prev
    Next
    INDEX
    Explanations

    path to or of

    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
    ARAM
    -0.10
     Corner
    -0.10
     hung
    -0.09
    _ranges
    -0.09
    hung
    -0.09
     audible
    -0.09
    ataka
    -0.09
    reachable
    -0.08
    Readable
    -0.08
    orge
    -0.08
    POSITIVE LOGITS
     path
    0.44
     paths
    0.32
    path
    0.29
     trajectory
    0.27
    -path
    0.26
     Path
    0.26
    è·¯å¾Ħ
    0.26
     course
    0.26
    /path
    0.26
    (path
    0.25
    Activations Density 0.126%

    No Known Activations