© 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. 49855
    Prev
    Next
    INDEX
    Explanations

    because or since

    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
    adel
    -0.09
    '])[
    -0.09
     oltre
    -0.09
     allo
    -0.09
    (be
    -0.08
    ;br
    -0.08
    ilan
    -0.08
     pá
    -0.08
    ,date
    -0.08
    /locale
    -0.08
    POSITIVE LOGITS
     because
    0.84
    because
    0.75
     Because
    0.58
    åĽł
    0.57
    Because
    0.56
     porque
    0.54
     since
    0.51
    since
    0.45
    ecause
    0.44
     karena
    0.43
    Activations Density 4.014%

    No Known Activations