© 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. 113050
    Prev
    Next
    INDEX
    Explanations

    validation and validity checks

    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
    ette
    -0.12
    ially
    -0.11
    WARD
    -0.11
    ialized
    -0.10
    lar
    -0.10
    ials
    -0.10
    /perl
    -0.10
    etting
    -0.10
    ward
    -0.10
    thest
    -0.10
    POSITIVE LOGITS
    atable
    0.14
    ating
    0.14
    ictory
    0.12
    ated
    0.11
    ity
    0.09
    atory
    0.09
    .isTrue
    0.09
    atin
    0.09
    igor
    0.08
    /cal
    0.08
    Activations Density 0.023%

    No Known Activations