© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89897
    Prev
    Next
    INDEX
    Explanations

    movement, paralysis, 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
     Kund
    -0.12
    ateg
    -0.11
    DT
    -0.11
     Gate
    -0.10
     absorption
    -0.10
     absorbing
    -0.10
     gate
    -0.10
     shelters
    -0.10
     sniff
    -0.09
     shelter
    -0.09
    POSITIVE LOGITS
     paralysis
    0.22
     paralyzed
    0.21
     movement
    0.18
     immobil
    0.18
     mov
    0.15
     mover
    0.15
     mobility
    0.15
     move
    0.15
     limbs
    0.15
     motor
    0.14
    Activations Density 0.088%

    No Known Activations