© 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. 88156
    Prev
    Next
    INDEX
    Explanations

    proven, shown, known, used

    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
    IMER
    -0.10
     particip
    -0.10
    quired
    -0.09
     contained
    -0.09
     attentive
    -0.09
    woke
    -0.09
    contained
    -0.09
     worthy
    -0.09
     invert
    -0.09
    agar
    -0.08
    POSITIVE LOGITS
     liken
    0.20
     proven
    0.17
     shown
    0.15
     outlaw
    0.14
     traditionally
    0.13
     debunk
    0.13
     theor
    0.12
     trademark
    0.12
     nicknamed
    0.12
     deemed
    0.11
    Activations Density 0.272%

    No Known Activations