© 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. 7534
    Prev
    Next
    INDEX
    Explanations

    sense and detect

    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
     visibility
    -0.11
     observable
    -0.11
    -scal
    -0.11
     Rub
    -0.11
     Observatory
    -0.10
     viewpoints
    -0.10
    -fashion
    -0.10
    /head
    -0.10
    urd
    -0.10
     Scal
    -0.10
    POSITIVE LOGITS
     change
    0.10
     disturbances
    0.09
     recip
    0.09
     changes
    0.09
     disturbance
    0.09
     Weston
    0.09
     hesitation
    0.08
    .ed
    0.08
     how
    0.08
     something
    0.08
    Activations Density 0.031%

    No Known Activations