© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    Xenopus and xenon words

    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
     Uns
    -0.13
     uns
    -0.09
     pent
    -0.09
     fre
    -0.09
    eurs
    -0.09
     Daisy
    -0.09
     Messages
    -0.08
     Unsafe
    -0.08
     Unsupported
    -0.08
    pees
    -0.08
    POSITIVE LOGITS
     Xen
    0.14
    ophobia
    0.13
     xen
    0.12
     reinc
    0.12
    arios
    0.11
    enga
    0.10
    engl
    0.10
     tremend
    0.10
    ophobic
    0.10
    stud
    0.09
    Activations Density 0.065%

    No Known Activations