© 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. 91166
    Prev
    Next
    INDEX
    Explanations

    parts of limbs

    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
     tent
    -0.09
    ht
    -0.09
    uga
    -0.09
     remorse
    -0.08
     adjacent
    -0.08
     Herr
    -0.08
     Adj
    -0.08
     wings
    -0.08
     Walton
    -0.08
    orig
    -0.08
    POSITIVE LOGITS
     fingertips
    0.18
     palm
    0.16
     fingers
    0.16
    -thumb
    0.16
     nails
    0.15
     fing
    0.14
     fingert
    0.14
     palms
    0.13
     nail
    0.13
     Palm
    0.13
    Activations Density 0.365%

    No Known Activations