© 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. 17965
    Prev
    Next
    INDEX
    Explanations

    sturdy, flimsy, weak, loose

    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
    e
    -0.10
    ries
    -0.09
     Erg
    -0.08
     residuals
    -0.08
     geh
    -0.08
    ping
    -0.08
     habit
    -0.08
    pe
    -0.08
    erk
    -0.08
    eration
    -0.08
    POSITIVE LOGITS
     loosely
    0.15
     weakest
    0.13
    iest
    0.12
     weak
    0.12
     loose
    0.11
    weak
    0.11
    Weak
    0.11
     cardboard
    0.11
    ailer
    0.11
    ily
    0.11
    Activations Density 0.001%

    No Known Activations