© 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. 50046
    Prev
    Next
    INDEX
    Explanations

    change for the better

    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
     Lim
    -0.10
    ymb
    -0.09
    823
    -0.09
    illac
    -0.09
    curacy
    -0.09
     Cur
    -0.09
    Lim
    -0.09
     NT
    -0.08
    ict
    -0.08
     Ce
    -0.08
    POSITIVE LOGITS
     worst
    0.42
     worse
    0.41
     Worst
    0.35
     Worse
    0.34
    wor
    0.20
     wors
    0.20
     best
    0.19
    best
    0.17
    orst
    0.16
     worsening
    0.15
    Activations Density 0.058%

    No Known Activations