© 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. 17917
    Prev
    Next
    INDEX
    Explanations

    practice and guidelines

    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
     practicing
    -0.11
     prakt
    -0.10
     practice
    -0.10
     practical
    -0.10
    olk
    -0.10
    spring
    -0.09
     practiced
    -0.09
     Practice
    -0.09
    åĪ¶
    -0.09
     prac
    -0.09
    POSITIVE LOGITS
    itioner
    0.15
    ijken
    0.11
    fully
    0.10
    zew
    0.10
    олж
    0.10
    able
    0.10
    uales
    0.09
    peare
    0.09
    ove
    0.09
    ownik
    0.09
    Activations Density 0.062%

    No Known Activations