© 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. 91276
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

    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
    uite
    -0.09
     overpower
    -0.09
    ays
    -0.09
     neigh
    -0.09
    å²ģ
    -0.08
    hare
    -0.08
    auce
    -0.08
     даннÑĭ
    -0.08
     resultant
    -0.08
     Done
    -0.08
    POSITIVE LOGITS
     is
    0.13
     called
    0.13
     provides
    0.13
     has
    0.12
     allows
    0.12
     itself
    0.12
     was
    0.11
     includes
    0.11
     known
    0.11
     aims
    0.11
    Activations Density 0.026%

    No Known Activations