© 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. 26520
    Prev
    Next
    INDEX
    Explanations

    incorrect or missing

    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
     benign
    -0.11
     innoc
    -0.10
     blackmail
    -0.10
     harmless
    -0.09
     inev
    -0.09
     traumatic
    -0.09
    ucz
    -0.09
     stab
    -0.09
    ISIS
    -0.09
     destructive
    -0.09
    POSITIVE LOGITS
     improperly
    0.27
     improper
    0.25
     insufficient
    0.22
     incorrectly
    0.21
     inadequate
    0.20
     incomplete
    0.19
     incorrect
    0.19
     missing
    0.18
     disob
    0.17
     tard
    0.17
    Activations Density 0.279%

    No Known Activations