© 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. 112352
    Prev
    Next
    INDEX
    Explanations

    Unplanned excision

    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
    illis
    -0.09
     fre
    -0.08
    orce
    -0.08
     dissip
    -0.08
     whence
    -0.08
    <|endoftext|>
    -0.08
     reconcile
    -0.08
    elle
    -0.08
    âŁ
    -0.08
    idl
    -0.08
    POSITIVE LOGITS
     Beau
    0.10
     weak
    0.10
     kir
    0.10
     Boo
    0.09
     Morm
    0.09
     Humanities
    0.09
     internals
    0.09
    /Dk
    0.09
     behavioural
    0.09
     bergen
    0.09
    Activations Density 0.010%

    No Known Activations