© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33849
    Prev
    Next
    INDEX
    Explanations

    tightening and tightness

    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
     pied
    -0.12
     Tear
    -0.11
     Stones
    -0.11
     tumble
    -0.11
     Needle
    -0.10
     stones
    -0.10
     curtain
    -0.10
    umbling
    -0.10
     flap
    -0.10
    ä¸Ģ页
    -0.10
    POSITIVE LOGITS
     tightening
    0.20
     tightened
    0.20
     tighter
    0.20
     tighten
    0.18
     tight
    0.17
     straps
    0.17
     constr
    0.16
     Tight
    0.16
     strap
    0.15
    tight
    0.14
    Activations Density 0.138%

    No Known Activations