© 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. 14628
    Prev
    Next
    INDEX
    Explanations

    links 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
    åĭ
    -0.10
    RESS
    -0.10
     gradually
    -0.09
     Ches
    -0.09
     Balk
    -0.08
     pornography
    -0.08
     slowly
    -0.08
     Holly
    -0.08
     Pastor
    -0.08
     Morr
    -0.08
    POSITIVE LOGITS
     invisible
    0.28
     unseen
    0.28
     Invisible
    0.23
     invis
    0.21
    invisible
    0.21
     audible
    0.19
     visible
    0.18
    visible
    0.16
     unheard
    0.15
     hidden
    0.15
    Activations Density 0.022%

    No Known Activations