© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29617
    Prev
    Next
    INDEX
    Explanations

    A|B testing or film production company

    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
    edom
    -0.08
     possession
    -0.08
     warm
    -0.07
     warmth
    -0.07
    aled
    -0.07
     gras
    -0.07
    tap
    -0.07
     transfers
    -0.07
    ako
    -0.07
     personally
    -0.07
    POSITIVE LOGITS
     Serv
    0.11
    Serv
    0.11
    cock
    0.10
     Fore
    0.10
     Griff
    0.10
    onne
    0.10
    akash
    0.10
     Nightmare
    0.10
    jax
    0.10
     Bomb
    0.10
    Activations Density 0.070%

    No Known Activations