© 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. 25866
    Prev
    Next
    INDEX
    Explanations

    prec followed by ut or ancerous or ursors

    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
    eing
    -0.12
    ered
    -0.10
    ech
    -0.10
    edar
    -0.10
    ual
    -0.10
    aque
    -0.10
    inally
    -0.10
    ucker
    -0.09
    urat
    -0.09
    ffen
    -0.09
    POSITIVE LOGITS
    ursors
    0.12
     prec
    0.11
    ocious
    0.10
    nev
    0.10
    ious
    0.09
    ollen
    0.09
    i
    0.09
     rel
    0.09
    iou
    0.09
    pub
    0.08
    Activations Density 0.006%

    No Known Activations