© 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. 47395
    Prev
    Next
    INDEX
    Explanations

    start sentence

    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
    eer
    -0.11
    rar
    -0.11
     Adler
    -0.10
    frag
    -0.10
     closets
    -0.10
    inan
    -0.10
    isse
    -0.09
    -l
    -0.09
     Hud
    -0.09
    aur
    -0.09
    POSITIVE LOGITS
    ove
    0.09
    gers
    0.09
    acht
    0.09
     screwed
    0.09
     Chap
    0.08
     Elliot
    0.08
    cmc
    0.08
    Nach
    0.08
     badly
    0.08
    alach
    0.08
    Activations Density 0.233%

    No Known Activations