© 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. 26944
    Prev
    Next
    INDEX
    Explanations

    script file extensions and connections

    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
     star
    -0.06
     flashback
    -0.06
    star
    -0.06
    -by
    -0.06
     meant
    -0.06
     novelty
    -0.06
     copyrighted
    -0.05
     Pace
    -0.05
     stamped
    -0.05
     Blo
    -0.05
    POSITIVE LOGITS
    uite
    0.14
    mux
    0.13
    feld
    0.12
    _Post
    0.12
     dere
    0.12
     criter
    0.12
     peri
    0.12
    _SA
    0.11
    SERVICE
    0.11
    olith
    0.11
    Activations Density 0.001%

    No Known Activations