© 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. 15475
    Prev
    Next
    INDEX
    Explanations

    make you

    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
     Ren
    -0.08
     interf
    -0.08
     congrat
    -0.08
     thankfully
    -0.08
     clever
    -0.08
    yth
    -0.08
     POSSIBILITY
    -0.08
    iani
    -0.07
     proportion
    -0.07
     Metro
    -0.07
    POSITIVE LOGITS
     anyone
    0.28
     anybody
    0.28
     any
    0.21
     Anyone
    0.21
    ä»»
    0.20
    Anyone
    0.18
     ANY
    0.17
    -any
    0.15
     instantly
    0.15
    Any
    0.15
    Activations Density 0.022%

    No Known Activations