© 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. 31390
    Prev
    Next
    INDEX
    Explanations

    background of context

    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
    ita
    -0.11
    ITA
    -0.10
    undefined
    -0.10
     Woodward
    -0.10
     undefined
    -0.10
    oner
    -0.10
    unden
    -0.10
     fut
    -0.10
     vg
    -0.10
    вод
    -0.09
    POSITIVE LOGITS
    èī²
    0.10
    ise
    0.10
     noise
    0.09
    /profile
    0.09
    íĻĶ
    0.09
     Noise
    0.08
    ed
    0.08
    -color
    0.08
    /ex
    0.08
     subtraction
    0.08
    Activations Density 0.055%

    No Known Activations