© 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. 112317
    Prev
    Next
    INDEX
    Explanations

    colon followed by word

    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
     cra
    -0.11
     Cin
    -0.10
    ling
    -0.10
     ZEND
    -0.10
    ewan
    -0.10
    rug
    -0.10
     Orr
    -0.10
     swamp
    -0.09
    utsch
    -0.09
    rts
    -0.09
    POSITIVE LOGITS
     OF
    0.09
     foregoing
    0.08
    /high
    0.08
    $type
    0.08
     particulars
    0.08
     Fox
    0.08
     staring
    0.08
     VIA
    0.08
    /gtest
    0.08
    ªĮ
    0.07
    Activations Density 0.703%

    No Known Activations