© 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. 25561
    Prev
    Next
    INDEX
    Explanations

    manipulate forms

    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
     chops
    -0.09
     å¯
    -0.09
     slowing
    -0.09
    esta
    -0.08
     interrupted
    -0.08
     dak
    -0.08
     suddenly
    -0.08
    éĸ
    -0.08
     Sanity
    -0.08
    isu
    -0.08
    POSITIVE LOGITS
     manipulate
    0.26
     Manip
    0.26
     manip
    0.26
     manipulation
    0.26
     manipulating
    0.26
     manipulated
    0.24
    Manip
    0.22
    /man
    0.17
     emotions
    0.17
     outcome
    0.13
    Activations Density 0.048%

    No Known Activations