© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31373
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    eed
    -0.09
    ainers
    -0.09
     desp
    -0.08
    Deg
    -0.08
     refr
    -0.08
     volum
    -0.08
    oly
    -0.08
    aina
    -0.08
     unconditional
    -0.08
    ode
    -0.07
    POSITIVE LOGITS
     fold
    0.11
     Aless
    0.10
    quiv
    0.10
    alli
    0.10
    abar
    0.10
     Tobias
    0.10
    (<
    0.10
     rede
    0.10
    undi
    0.10
    (--
    0.10
    Activations Density 0.015%

    No Known Activations