© 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. 33365
    Prev
    Next
    INDEX
    Explanations

    text starting with H, J, G, B, P

    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
    _mB
    -0.10
    ibi
    -0.09
    ibu
    -0.09
    _mE
    -0.08
    onta
    -0.08
     unp
    -0.08
    ROI
    -0.08
    _mC
    -0.08
    Tau
    -0.08
    eni
    -0.08
    POSITIVE LOGITS
    609
    0.10
     Roz
    0.10
     Vig
    0.09
    vig
    0.09
     te
    0.09
     safeguard
    0.09
     Push
    0.09
     Vick
    0.09
    ams
    0.09
     recess
    0.09
    Activations Density 0.224%

    No Known Activations