© 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. 33410
    Prev
    Next
    INDEX
    Explanations

    loose and lax fitting

    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
     cris
    -0.09
    hton
    -0.09
    ese
    -0.09
    ogi
    -0.09
    -Smith
    -0.08
     equip
    -0.08
     dese
    -0.08
     volte
    -0.08
     Juni
    -0.08
    force
    -0.08
    POSITIVE LOGITS
     loose
    0.29
     Loose
    0.23
     loosen
    0.22
     loos
    0.22
     loosely
    0.19
     lax
    0.17
    Lo
    0.15
     Lo
    0.13
     sloppy
    0.12
     relaxed
    0.12
    Activations Density 0.019%

    No Known Activations