© 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. 27931
    Prev
    Next
    INDEX
    Explanations

    list of conditions

    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
    itar
    -0.13
    upy
    -0.11
    ilst
    -0.11
    .Level
    -0.11
     fiss
    -0.11
    edere
    -0.11
    uhe
    -0.11
    bose
    -0.11
    ouns
    -0.11
    upuncture
    -0.11
    POSITIVE LOGITS
    rax
    0.08
    Longrightarrow
    0.07
     Replay
    0.07
     Lonely
    0.07
     imper
    0.06
     serge
    0.06
     Kate
    0.06
    andle
    0.06
     Imper
    0.06
    ldr
    0.06
    Activations Density 0.001%

    No Known Activations