© 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. 7299
    Prev
    Next
    INDEX
    Explanations

    dip / dipping / dipped / dips

    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
     clos
    -0.11
    erek
    -0.09
    edu
    -0.09
    (dead
    -0.09
    amas
    -0.09
    wert
    -0.08
    oppable
    -0.08
     tight
    -0.08
     kick
    -0.08
     Buster
    -0.08
    POSITIVE LOGITS
     dip
    0.22
     dipping
    0.22
     dipped
    0.21
     dips
    0.20
     Dip
    0.20
     pools
    0.14
     pool
    0.13
     into
    0.12
     toes
    0.12
     bucket
    0.12
    Activations Density 0.012%

    No Known Activations