© 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. 17561
    Prev
    Next
    INDEX
    Explanations

    push forward

    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
    ossal
    -0.10
    ERR
    -0.10
    odia
    -0.09
    ride
    -0.09
     invers
    -0.09
     keer
    -0.09
    edar
    -0.09
     generado
    -0.09
    unsch
    -0.08
    bé
    -0.08
    POSITIVE LOGITS
     boundaries
    0.12
     away
    0.10
     rou
    0.10
     boundary
    0.10
     Vict
    0.10
     Boundary
    0.10
    uid
    0.10
    avr
    0.09
    155
    0.09
    cole
    0.09
    Activations Density 0.003%

    No Known Activations