© 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. 30284
    Prev
    Next
    INDEX
    Explanations

    Essential context after "essential"

    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
    VID
    -0.09
    vid
    -0.09
     Nass
    -0.08
    gv
    -0.07
     Joh
    -0.07
    cus
    -0.07
     Ach
    -0.07
    eder
    -0.07
    707
    -0.07
    ล
    -0.07
    POSITIVE LOGITS
     oils
    0.17
    ArgsConstructor
    0.15
     Evil
    0.15
     nutrients
    0.14
     evil
    0.14
    raz
    0.13
     evils
    0.13
    uset
    0.13
    evil
    0.12
    bak
    0.12
    Activations Density 0.095%

    No Known Activations