© 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. 26143
    Prev
    Next
    INDEX
    Explanations

    yachts, yore, yew, Yunnan, yurts

    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
     triangular
    -0.10
     implied
    -0.09
     tac
    -0.09
    s
    -0.08
    isko
    -0.08
    ii
    -0.08
     Khal
    -0.08
    uali
    -0.08
    izard
    -0.08
    me
    -0.08
    POSITIVE LOGITS
    atra
    0.13
    arat
    0.12
    upe
    0.12
    achts
    0.11
     Hanson
    0.11
    abbo
    0.10
    ogan
    0.10
    ador
    0.10
    anal
    0.10
    enido
    0.10
    Activations Density 0.041%

    No Known Activations