© 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. 28966
    Prev
    Next
    INDEX
    Explanations

    display device

    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
     conditioned
    -0.10
    yen
    -0.09
     Eb
    -0.09
    ality
    -0.08
    kh
    -0.08
    uel
    -0.08
     lokal
    -0.07
    uality
    -0.07
     Coleman
    -0.07
    gor
    -0.07
    POSITIVE LOGITS
     display
    0.11
    HomeAsUpEnabled
    0.11
    ossa
    0.10
     gravity
    0.10
    able
    0.10
    -intensive
    0.10
    eyed
    0.10
    elon
    0.10
     showing
    0.10
    rgan
    0.10
    Activations Density 0.033%

    No Known Activations