© 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. 50600
    Prev
    Next
    INDEX
    Explanations

    plastic manufacturing and chemicals

    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
    éĸĵ
    -0.11
    vsp
    -0.10
     Replay
    -0.10
     Tür
    -0.10
    ~=
    -0.10
    lia
    -0.09
     truncate
    -0.09
    eci
    -0.09
    Atom
    -0.09
    coc
    -0.09
    POSITIVE LOGITS
     manufacturing
    0.18
     factory
    0.17
     Manufacturing
    0.15
     plastic
    0.15
     factories
    0.14
     smell
    0.13
     residual
    0.13
     plastics
    0.13
     Plastic
    0.13
    Manufact
    0.13
    Activations Density 0.045%

    No Known Activations