© 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. 33425
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     Valent
    -0.12
     agre
    -0.11
     piss
    -0.10
     Thor
    -0.10
    imple
    -0.10
    modulo
    -0.09
    ableObject
    -0.09
     tol
    -0.09
     woll
    -0.09
    /details
    -0.09
    POSITIVE LOGITS
    ibs
    0.09
    ots
    0.09
     Ronnie
    0.08
     axis
    0.08
    ABI
    0.08
    arna
    0.08
     Bulls
    0.07
    ola
    0.07
    ochrome
    0.07
     bild
    0.07
    Activations Density 0.036%

    No Known Activations