© 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. 47117
    Prev
    Next
    INDEX
    Explanations

    without any

    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
    illos
    -0.11
     Payne
    -0.10
     POSIX
    -0.09
    atat
    -0.09
    ixo
    -0.09
    607
    -0.09
     defensively
    -0.09
     Schl
    -0.09
     lord
    -0.09
     Norris
    -0.08
    POSITIVE LOGITS
     hassle
    0.13
     hesitation
    0.12
     any
    0.12
     hass
    0.12
    ä»»
    0.11
     complains
    0.11
     hes
    0.11
     anyhow
    0.10
    -any
    0.10
     Fut
    0.10
    Activations Density 0.098%

    No Known Activations