© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    falling or settling down

    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
     hypoth
    -0.09
     trib
    -0.09
    traction
    -0.09
     horizon
    -0.09
     hitch
    -0.09
     acad
    -0.09
     surfing
    -0.09
     brief
    -0.08
     Hitch
    -0.08
    ynn
    -0.08
    POSITIVE LOGITS
     onto
    0.15
     flop
    0.14
     slack
    0.14
     flo
    0.12
    afil
    0.12
     limp
    0.11
    Flo
    0.11
     slap
    0.11
     slump
    0.11
     doubled
    0.11
    Activations Density 0.017%

    No Known Activations