© 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. 90010
    Prev
    Next
    INDEX
    Explanations

    particularly regarding

    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
    oret
    -0.15
    quoi
    -0.12
     zwar
    -0.12
    US
    -0.11
    oriously
    -0.11
    or
    -0.10
    #End
    -0.10
    ina
    -0.10
    &s
    -0.10
    cest
    -0.10
    POSITIVE LOGITS
    ,
    0.11
    -,
    0.08
    ses
    0.08
    ,</
    0.07
     Wig
    0.07
    tol
    0.07
     Aqu
    0.07
     Rach
    0.06
    315
    0.06
     bod
    0.06
    Activations Density 1.698%

    No Known Activations