© 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. 14799
    Prev
    Next
    INDEX
    Explanations

    body parts, relationship terms

    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
     Sno
    -0.11
     incorpor
    -0.09
     craw
    -0.09
     postponed
    -0.09
    ampo
    -0.09
     Copp
    -0.09
    Unnamed
    -0.09
     altern
    -0.09
     UV
    -0.08
    inkel
    -0.08
    POSITIVE LOGITS
     body
    0.14
     thigh
    0.13
     bodies
    0.12
     waist
    0.12
    -body
    0.11
     Body
    0.11
     thighs
    0.11
     bodily
    0.11
     flush
    0.11
     Bodies
    0.11
    Activations Density 0.003%

    No Known Activations