© 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. 25524
    Prev
    Next
    INDEX
    Explanations

    years or dates

    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
    loid
    -0.09
    acers
    -0.08
    åıĭ
    -0.08
    die
    -0.08
    ê
    -0.08
    ï
    -0.08
    lical
    -0.08
    opp
    -0.08
     foul
    -0.08
     publicity
    -0.08
    POSITIVE LOGITS
    s
    0.17
    ï¸ı
    0.11
    sip
    0.10
    samp
    0.10
    nal
    0.10
    ned
    0.09
    sampling
    0.09
    redo
    0.09
    voor
    0.09
     “
    0.09
    Activations Density 0.002%

    No Known Activations