© 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. 50460
    Prev
    Next
    INDEX
    Explanations

    call to action

    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
     usually
    -0.13
    Usually
    -0.11
    usually
    -0.10
     Usually
    -0.10
     indirectly
    -0.10
     normally
    -0.09
     hap
    -0.09
     fil
    -0.09
    UNCTION
    -0.08
    previous
    -0.08
    POSITIVE LOGITS
     collectively
    0.20
     ourselves
    0.17
     Stop
    0.16
     urgently
    0.16
     stop
    0.14
     rethink
    0.14
     STOP
    0.14
     everywhere
    0.14
    Stop
    0.14
     educate
    0.13
    Activations Density 0.245%

    No Known Activations