© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5958
    Prev
    Next
    INDEX
    Explanations

    this time

    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
    isser
    -0.09
     rather
    -0.09
    ani
    -0.08
     cont
    -0.08
     anymore
    -0.08
    /stream
    -0.08
    asan
    -0.08
    icone
    -0.08
     statt
    -0.08
    ach
    -0.08
    POSITIVE LOGITS
     this
    0.21
    this
    0.19
    	this
    0.16
    -this
    0.15
    (this
    0.15
     harder
    0.14
    ,this
    0.14
     quieter
    0.14
     stronger
    0.14
    =this
    0.14
    Activations Density 0.147%

    No Known Activations