© 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. 46857
    Prev
    Next
    INDEX
    Explanations

    register post thread

    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
    ighth
    -0.09
     princess
    -0.09
    æ¥
    -0.08
    /form
    -0.08
    ipt
    -0.08
     ladies
    -0.08
    sto
    -0.08
     urn
    -0.08
     invers
    -0.08
     slump
    -0.07
    POSITIVE LOGITS
     serge
    0.10
     synchron
    0.10
     Bord
    0.10
     Bes
    0.09
     Detector
    0.09
    adar
    0.09
     Drain
    0.09
    /show
    0.09
     threaded
    0.09
    OSC
    0.09
    Activations Density 0.003%

    No Known Activations