© 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. 33443
    Prev
    Next
    INDEX
    Explanations

    progress and turning

    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
    amac
    -0.07
     DS
    -0.06
     bes
    -0.06
    prd
    -0.06
    adr
    -0.06
     Hogan
    -0.06
    ÃĤ
    -0.06
    lingen
    -0.06
    mony
    -0.06
    uther
    -0.05
    POSITIVE LOGITS
    >((
    0.12
     Thur
    0.11
     Fou
    0.11
    .bo
    0.11
     Que
    0.10
     Ting
    0.10
    /native
    0.10
    752
    0.10
    apon
    0.10
    seller
    0.10
    Activations Density 0.164%

    No Known Activations