© 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. 17906
    Prev
    Next
    INDEX
    Explanations

    guest speaker or room

    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
    thal
    -0.12
    lep
    -0.11
    ALLY
    -0.11
    /OR
    -0.10
    mb
    -0.10
    ously
    -0.10
    oux
    -0.10
    pta
    -0.10
    ëĭ¹
    -0.10
    -dot
    -0.09
    POSITIVE LOGITS
    imates
    0.17
    imate
    0.15
    book
    0.12
     speakers
    0.10
     guests
    0.10
    guest
    0.10
    imation
    0.09
    imating
    0.09
     speaker
    0.09
     arriving
    0.09
    Activations Density 0.010%

    No Known Activations