© 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. 28830
    Prev
    Next
    INDEX
    Explanations

    epic poem, quests, loot, land

    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
    onal
    -0.10
     lud
    -0.09
     Hayward
    -0.08
    /usr
    -0.08
     dil
    -0.07
     equ
    -0.07
     obst
    -0.07
    pering
    -0.07
    lining
    -0.07
    ewire
    -0.07
    POSITIVE LOGITS
    enter
    0.13
    entre
    0.13
     ocas
    0.12
    ardi
    0.12
     Bes
    0.11
     digs
    0.11
     altogether
    0.11
     fucks
    0.10
     outright
    0.10
    ENTER
    0.10
    Activations Density 0.005%

    No Known Activations