© 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. 17110
    Prev
    Next
    INDEX
    Explanations

    tail area

    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
     throat
    -0.13
     wrist
    -0.11
     Coil
    -0.11
     Breast
    -0.11
    throat
    -0.10
     slee
    -0.10
     multis
    -0.10
     wrists
    -0.10
     Niagara
    -0.09
     scalp
    -0.09
    POSITIVE LOGITS
     rear
    0.16
     butto
    0.14
     tail
    0.14
    rear
    0.14
    Tail
    0.13
     posterior
    0.13
     Tail
    0.12
     rim
    0.12
     stool
    0.12
     cracking
    0.12
    Activations Density 0.128%

    No Known Activations