© 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. 48718
    Prev
    Next
    INDEX
    Explanations

    NO. [number]

    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
     Phill
    -0.09
     amort
    -0.08
    prung
    -0.08
    pta
    -0.07
    nen
    -0.07
     nearly
    -0.07
    -muted
    -0.07
     damning
    -0.07
    Italic
    -0.07
     uncont
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.17
    plode
    0.15
    AlgorithmException
    0.13
    /no
    0.12
    ,No
    0.12
    ElementException
    0.11
    escape
    0.09
    lez
    0.09
     bueno
    0.09
     Lorem
    0.09
    Activations Density 0.458%

    No Known Activations