© 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. 4204
    Prev
    Next
    INDEX
    Explanations

    push-pull actions

    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
     spherical
    -0.09
     Urb
    -0.07
     Roman
    -0.07
    into
    -0.07
     Luca
    -0.07
     Gaut
    -0.07
    cio
    -0.07
     REAL
    -0.07
     reduced
    -0.07
    ind
    -0.07
    POSITIVE LOGITS
    acco
    0.11
    /interfaces
    0.10
    lse
    0.10
    ichel
    0.10
     earm
    0.10
    kor
    0.10
    accent
    0.10
    emarks
    0.10
    ringe
    0.10
    uby
    0.10
    Activations Density 0.001%

    No Known Activations