© 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. 91339
    Prev
    Next
    INDEX
    Explanations

    smack or parked, ending in -ed, -on, -up, -out

    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
     untouched
    -0.10
     volte
    -0.10
     refr
    -0.10
     Blake
    -0.10
     upward
    -0.10
     Duffy
    -0.10
     unheard
    -0.10
    inger
    -0.10
    eden
    -0.10
    ±Ð¾ÑĤ
    -0.10
    POSITIVE LOGITS
     squarely
    0.16
     smack
    0.16
     firmly
    0.15
     atop
    0.13
     onto
    0.12
     Seats
    0.12
     Seat
    0.10
     on
    0.09
     comfortably
    0.09
    onto
    0.09
    Activations Density 0.020%

    No Known Activations