© 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. 26743
    Prev
    Next
    INDEX
    Explanations

    body parts and systems

    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
     Lent
    -0.09
     wet
    -0.09
     unseen
    -0.08
    andler
    -0.08
     proced
    -0.08
    ÑģÑĤи
    -0.08
     rights
    -0.07
     terminals
    -0.07
    raw
    -0.07
    aden
    -0.07
    POSITIVE LOGITS
     body
    0.20
    body
    0.17
     Body
    0.16
    -body
    0.15
     neighbouring
    0.15
     torso
    0.15
    Body
    0.14
    身
    0.14
     BODY
    0.14
    BODY
    0.14
    Activations Density 0.426%

    No Known Activations