© 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. 116077
    Prev
    Next
    INDEX
    Explanations

    initials or 'M' followed by specific suffixes

    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
    ag
    -0.11
    OD
    -0.11
    eter
    -0.11
    ouse
    -0.11
    arg
    -0.11
    iss
    -0.10
    ove
    -0.10
    ODE
    -0.10
    atch
    -0.10
    oney
    -0.10
    POSITIVE LOGITS
    roz
    0.18
    endoza
    0.17
    cd
    0.15
    laden
    0.15
    istry
    0.15
    udget
    0.15
    cc
    0.14
    á»Ļt
    0.14
    iddled
    0.14
    cke
    0.14
    Activations Density 0.302%

    No Known Activations