© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18393
    Prev
    Next
    INDEX
    Explanations

    Ryan Faughnder, Copyright, names

    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
     xhttp
    -0.08
    ,std
    -0.07
    å£
    -0.07
     upstream
    -0.07
    .comp
    -0.07
     ########.
    -0.07
    .FragmentManager
    -0.07
    _span
    -0.07
     vero
    -0.07
     scripted
    -0.07
    POSITIVE LOGITS
    .HttpServletResponse
    0.10
     revelation
    0.09
     MessageBoxIcon
    0.09
    Drv
    0.09
    Spi
    0.08
    _proc
    0.08
     #$
    0.08
    (ml
    0.08
    &q
    0.08
     acl
    0.08
    Activations Density 1.896%

    No Known Activations