© 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. 28085
    Prev
    Next
    INDEX
    Explanations

    additionally, additional, data, notes, information

    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
     additions
    -0.12
    iaux
    -0.12
    land
    -0.11
    eus
    -0.11
    hound
    -0.10
    leigh
    -0.10
    box
    -0.09
    est
    -0.09
    foot
    -0.09
    eil
    -0.09
    POSITIVE LOGITS
    y
    0.14
    nal
    0.14
    /sub
    0.13
    ity
    0.12
    /Sub
    0.11
    ALLY
    0.10
    ities
    0.10
    yi
    0.10
    ality
    0.10
    mente
    0.10
    Activations Density 0.046%

    No Known Activations