© 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. 113030
    Prev
    Next
    INDEX
    Explanations

    physical posture and states

    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
    orf
    -0.10
     dere
    -0.09
     Gos
    -0.09
     shower
    -0.09
     dew
    -0.09
     Cle
    -0.08
     Dere
    -0.08
     beef
    -0.08
    ué
    -0.08
    aul
    -0.08
    POSITIVE LOGITS
     standing
    0.36
     Standing
    0.29
    Standing
    0.24
    standing
    0.24
     stood
    0.24
    -standing
    0.23
     stand
    0.22
     stands
    0.21
     seated
    0.21
     kneeling
    0.21
    Activations Density 0.082%

    No Known Activations