© 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. 115937
    Prev
    Next
    INDEX
    Explanations

    digestive tract parts

    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
     stomach
    -0.25
    Digest
    -0.19
     belly
    -0.18
     Digest
    -0.17
     digestive
    -0.16
     gastrointestinal
    -0.16
     digestion
    -0.16
     Belly
    -0.14
     abdomen
    -0.14
    igest
    -0.13
    POSITIVE LOGITS
     thighs
    0.10
     limbs
    0.09
    wordpress
    0.09
    wed
    0.08
     keyword
    0.08
     thigh
    0.08
     pledge
    0.08
    owa
    0.08
    ORM
    0.08
    è¿ĩ
    0.08
    Activations Density 0.162%

    No Known Activations