© 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. 30047
    Prev
    Next
    INDEX
    Explanations

    enough

    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
     McKay
    -0.09
    Checkpoint
    -0.09
    ika
    -0.09
    preci
    -0.09
    ymi
    -0.09
     meas
    -0.09
     Reco
    -0.09
     Redistributions
    -0.09
    /view
    -0.09
    nor
    -0.09
    POSITIVE LOGITS
     needless
    0.30
     Enough
    0.26
     Needless
    0.24
     Need
    0.24
     need
    0.23
    Need
    0.23
     enough
    0.22
    need
    0.21
     obvious
    0.21
     Suff
    0.21
    Activations Density 0.214%

    No Known Activations