© 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. 16835
    Prev
    Next
    INDEX
    Explanations

    right edge or side

    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
     lakes
    -0.10
    oth
    -0.09
     âĿ
    -0.09
     Lakes
    -0.09
     Toolbar
    -0.09
     Fourth
    -0.08
    fen
    -0.08
     protested
    -0.08
     fourth
    -0.08
     Till
    -0.08
    POSITIVE LOGITS
    åı³
    0.26
    -right
    0.24
     right
    0.22
    _right
    0.22
    (right
    0.22
    .right
    0.21
    right
    0.21
     Right
    0.21
    	right
    0.20
    /right
    0.20
    Activations Density 0.278%

    No Known Activations