© 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. 17235
    Prev
    Next
    INDEX
    Explanations

    actively creating or making

    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
    -conscious
    -0.09
    anh
    -0.09
    aku
    -0.08
     unintended
    -0.08
     Mans
    -0.08
     conscious
    -0.08
    enen
    -0.08
     Morse
    -0.08
     Bullet
    -0.08
    iman
    -0.08
    POSITIVE LOGITS
     own
    0.21
    own
    0.21
     Own
    0.17
     OWN
    0.17
    _own
    0.16
     themselves
    0.15
     actual
    0.15
     participate
    0.15
     actually
    0.15
     actively
    0.14
    Activations Density 0.713%

    No Known Activations