© 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. 89209
    Prev
    Next
    INDEX
    Explanations

    password and login details

    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
     polym
    -0.10
     Kurt
    -0.10
     todd
    -0.10
    RFC
    -0.09
     Vlad
    -0.09
    ido
    -0.09
    .BigDecimal
    -0.09
     discontin
    -0.09
    asper
    -0.08
     Pruitt
    -0.08
    POSITIVE LOGITS
     confirmPassword
    0.13
     wanna
    0.09
     acct
    0.09
     drip
    0.09
     butt
    0.09
    .WebElement
    0.08
    quine
    0.08
    <iostream
    0.08
    iken
    0.08
     STL
    0.08
    Activations Density 0.060%

    No Known Activations