© 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. 46755
    Prev
    Next
    INDEX
    Explanations

    trans- prefix and its continuations

    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
    ton
    -0.10
     matter
    -0.10
    ost
    -0.09
     hone
    -0.09
    ESIS
    -0.09
     earnest
    -0.09
    inho
    -0.09
    ç¤
    -0.09
    aoke
    -0.09
    thing
    -0.08
    POSITIVE LOGITS
     transf
    0.19
     trans
    0.16
     Trans
    0.15
     TRANS
    0.14
     transpose
    0.14
    /trans
    0.14
    (trans
    0.14
     transl
    0.13
     transplant
    0.13
    Trans
    0.13
    Activations Density 0.044%

    No Known Activations