© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31771
    Prev
    Next
    INDEX
    Explanations

    care / health / doubt

    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
    eko
    -0.09
    ISCO
    -0.09
     scouting
    -0.08
    ledge
    -0.08
    apore
    -0.08
    strup
    -0.08
     Auss
    -0.08
    ppo
    -0.08
     vou
    -0.08
    ois
    -0.07
    POSITIVE LOGITS
     fuck
    0.13
    fuck
    0.11
     HOWEVER
    0.11
    lime
    0.11
     blah
    0.11
     priv
    0.10
     lil
    0.10
     ban
    0.10
     cam
    0.10
    chl
    0.10
    Activations Density 0.009%

    No Known Activations