© 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. 91284
    Prev
    Next
    INDEX
    Explanations

    influence or effect

    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
     undergo
    -0.13
     ren
    -0.11
     contemplate
    -0.11
     attempt
    -0.11
     abst
    -0.11
     scrutin
    -0.11
     retry
    -0.11
     abandon
    -0.11
    remember
    -0.10
     Particip
    -0.10
    POSITIVE LOGITS
     convince
    0.22
     scare
    0.17
     fright
    0.17
     confuse
    0.17
     convin
    0.16
     encourage
    0.15
     distract
    0.15
     impress
    0.15
     terr
    0.15
     inspire
    0.15
    Activations Density 0.077%

    No Known Activations