© 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. 33096
    Prev
    Next
    INDEX
    Explanations

    parts of bodies or mechanisms

    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
    iat
    -0.12
    scriptions
    -0.11
    edia
    -0.11
    quisitions
    -0.10
     buz
    -0.10
    iations
    -0.10
    imens
    -0.10
     lump
    -0.10
    IRM
    -0.10
    Listing
    -0.10
    POSITIVE LOGITS
     fingers
    0.12
     arteries
    0.10
     forks
    0.10
     letters
    0.10
     ears
    0.10
     joints
    0.09
     hinges
    0.09
     two
    0.09
     four
    0.09
     molecules
    0.09
    Activations Density 0.039%

    No Known Activations