© 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. 4806
    Prev
    Next
    INDEX
    Explanations

    VIP or priority access

    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
    eva
    -0.11
    ives
    -0.11
    annes
    -0.11
    amientos
    -0.11
    earth
    -0.10
    enia
    -0.10
    agle
    -0.10
    lew
    -0.10
     eth
    -0.10
    IVES
    -0.09
    POSITIVE LOGITS
    -level
    0.10
     status
    0.10
     access
    0.09
     vip
    0.09
     unfinished
    0.09
    -worthy
    0.09
     guests
    0.09
    urr
    0.09
     level
    0.09
     VIP
    0.08
    Activations Density 0.006%

    No Known Activations