© 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. 91789
    Prev
    Next
    INDEX
    Explanations

    conditions of distribution and use

    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
     Bail
    -0.10
     Journey
    -0.09
     constituted
    -0.09
     âĿ¤
    -0.09
    abr
    -0.09
     Indeed
    -0.09
     FU
    -0.09
     alterations
    -0.08
    jour
    -0.08
     Woj
    -0.08
    POSITIVE LOGITS
     repe
    0.09
     collateral
    0.09
     restraint
    0.08
     Tran
    0.08
    ëĤĺ
    0.08
    Spr
    0.08
    zza
    0.07
     Echo
    0.07
    (kind
    0.07
    ND
    0.07
    Activations Density 0.016%

    No Known Activations