© 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. 7481
    Prev
    Next
    INDEX
    Explanations

    how something works

    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
    )?.
    -0.09
    /chart
    -0.08
     Suit
    -0.08
     Ways
    -0.08
    PIP
    -0.08
    isch
    -0.08
     adapt
    -0.08
    lint
    -0.08
    ISR
    -0.08
    adro
    -0.08
    POSITIVE LOGITS
     works
    0.23
     Works
    0.22
     workings
    0.21
     operates
    0.19
     worked
    0.17
     funciona
    0.16
     mechanics
    0.16
     operate
    0.16
    Works
    0.16
     mechanism
    0.15
    Activations Density 0.578%

    No Known Activations