© 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. 50359
    Prev
    Next
    INDEX
    Explanations

    perfect / ideal

    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
    ilon
    -0.13
    oli
    -0.10
    yne
    -0.10
    achen
    -0.10
    ts
    -0.09
    ÑĤÑĥ
    -0.09
     ness
    -0.09
    ensi
    -0.09
     Funny
    -0.09
    fy
    -0.09
    POSITIVE LOGITS
     perfect
    0.16
    perfect
    0.13
    Perfect
    0.13
     Perfect
    0.12
     for
    0.10
     candidates
    0.09
     Candidates
    0.09
     opportunity
    0.09
     prefect
    0.09
     compliment
    0.08
    Activations Density 0.024%

    No Known Activations