© 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. 112593
    Prev
    Next
    INDEX
    Explanations

    instructions or advice

    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
    ucken
    -0.13
    avad
    -0.13
    andin
    -0.12
     defaulted
    -0.11
    mere
    -0.11
    eniable
    -0.11
    afil
    -0.11
     rigged
    -0.11
    osto
    -0.11
     intimid
    -0.10
    POSITIVE LOGITS
     caution
    0.20
     appropriate
    0.19
     proper
    0.18
     reputable
    0.18
     responsibly
    0.15
     discretion
    0.13
     wisely
    0.13
     correct
    0.13
     respectful
    0.13
     sparing
    0.12
    Activations Density 0.146%

    No Known Activations