© 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. 4691
    Prev
    Next
    INDEX
    Explanations

    collaboration and embracing progress

    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
     hardened
    -0.11
     painstaking
    -0.11
     ascertain
    -0.11
     satisfy
    -0.10
     prestige
    -0.09
     stren
    -0.09
    inka
    -0.09
     orderly
    -0.09
     ers
    -0.09
    Legend
    -0.09
    POSITIVE LOGITS
     transformative
    0.15
     embracing
    0.15
     incorporating
    0.14
     unlocking
    0.14
    embr
    0.14
     holistic
    0.14
     Incorpor
    0.14
     embrace
    0.14
     Hol
    0.13
    Harness
    0.13
    Activations Density 0.025%

    No Known Activations