© 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. 32003
    Prev
    Next
    INDEX
    Explanations

    cleanliness and usage

    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
    ASE
    -0.09
    ase
    -0.09
    aison
    -0.08
    mented
    -0.08
     Gron
    -0.07
    gne
    -0.07
    lei
    -0.07
    elles
    -0.07
    loth
    -0.07
    s
    -0.07
    POSITIVE LOGITS
    -cut
    0.24
    (er
    0.22
     slate
    0.20
    liness
    0.20
    est
    0.19
     Slate
    0.17
    ups
    0.15
    Cut
    0.14
    ings
    0.14
    thes
    0.14
    Activations Density 0.023%

    No Known Activations