© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    messing around, playing with

    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
    rah
    -0.11
     salt
    -0.10
     bail
    -0.10
     argent
    -0.10
    wide
    -0.09
     indemn
    -0.09
     carn
    -0.09
     motivating
    -0.09
     wide
    -0.09
     incarn
    -0.09
    POSITIVE LOGITS
     knobs
    0.22
     tink
    0.22
     knob
    0.18
     manipulate
    0.17
     manipulating
    0.17
     manipulation
    0.16
     manipulated
    0.15
     manip
    0.15
     tweaking
    0.15
     Manip
    0.14
    Activations Density 0.133%

    No Known Activations