© 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. 91460
    Prev
    Next
    INDEX
    Explanations

    all or nothing

    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
     tremendously
    -0.10
     wisely
    -0.10
     bele
    -0.09
    omet
    -0.09
     truly
    -0.08
    ogan
    -0.08
     supposedly
    -0.08
     terribly
    -0.08
     Wol
    -0.08
     somehow
    -0.07
    POSITIVE LOGITS
     unchanged
    0.18
     impossible
    0.17
     monopoly
    0.17
     imposs
    0.17
     exclusively
    0.16
     Impossible
    0.15
     limitless
    0.15
     unanimously
    0.15
     guaranteed
    0.15
     identical
    0.15
    Activations Density 0.201%

    No Known Activations