© 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. 48170
    Prev
    Next
    INDEX
    Explanations

    get rid of

    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
    lin
    -0.10
     Fax
    -0.10
    LIN
    -0.10
    quan
    -0.10
     omission
    -0.10
     apart
    -0.10
     omitted
    -0.10
    lyn
    -0.10
    orgot
    -0.10
     obliv
    -0.10
    POSITIVE LOGITS
     pes
    0.11
     unwanted
    0.11
     excess
    0.10
     surplus
    0.10
     Accent
    0.09
    /control
    0.09
    gor
    0.09
    ored
    0.09
    ugu
    0.08
    Accent
    0.08
    Activations Density 0.029%

    No Known Activations