© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27925
    Prev
    Next
    INDEX
    Explanations

    perc/pers followed by specific endings

    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
     score
    -0.09
    avit
    -0.08
     rond
    -0.08
    uther
    -0.08
    oad
    -0.08
    hek
    -0.08
    acle
    -0.07
    lix
    -0.07
    ав
    -0.07
     Bruce
    -0.07
    POSITIVE LOGITS
     perseverance
    0.17
     perse
    0.17
     pers
    0.16
     persistence
    0.15
    (per
    0.15
     perm
    0.15
    /per
    0.14
     persever
    0.14
     pixel
    0.14
     perc
    0.14
    Activations Density 0.067%

    No Known Activations