© 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. 49145
    Prev
    Next
    INDEX
    Explanations

    the idea is to

    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
    ĵĺ
    -0.13
    öl
    -0.12
     Uph
    -0.11
     cad
    -0.10
     cadre
    -0.10
    TestClass
    -0.10
    anan
    -0.10
     Dickinson
    -0.10
    umas
    -0.10
     ITE
    -0.09
    POSITIVE LOGITS
     not
    0.12
     simplicity
    0.11
     supposed
    0.10
     tw
    0.09
     creating
    0.09
    amin
    0.09
     create
    0.09
     NOT
    0.09
     familiarity
    0.09
     YE
    0.08
    Activations Density 0.231%

    No Known Activations