© 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. 90820
    Prev
    Next
    INDEX
    Explanations

    private email, background tasks, open beta, members page

    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
    izu
    -0.09
    -looking
    -0.08
    BX
    -0.08
    /w
    -0.08
     mon
    -0.08
     somewhat
    -0.08
    -w
    -0.07
     som
    -0.07
     Sears
    -0.07
    ased
    -0.07
    POSITIVE LOGITS
     session
    0.15
     sessions
    0.14
    /session
    0.13
     room
    0.13
     mode
    0.12
    -session
    0.12
     rooms
    0.12
     Sessions
    0.12
    OOM
    0.12
    session
    0.11
    Activations Density 0.005%

    No Known Activations