© 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. 33804
    Prev
    Next
    INDEX
    Explanations

    explaining why or what is behind something

    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
     Miscellaneous
    -0.09
     intervening
    -0.08
    ober
    -0.08
    ortho
    -0.07
     Klaus
    -0.07
     overlapping
    -0.07
     safeguards
    -0.07
     Means
    -0.07
     steadfast
    -0.07
     Whit
    -0.07
    POSITIVE LOGITS
     Behind
    0.15
     why
    0.15
     behind
    0.15
     WHY
    0.13
     curtain
    0.13
    beh
    0.13
    why
    0.13
    Behind
    0.13
    nuts
    0.13
    ebin
    0.12
    Activations Density 0.030%

    No Known Activations