© 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. 26449
    Prev
    Next
    INDEX
    Explanations

    imagination and its use

    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
    /qu
    -0.11
    /ac
    -0.11
     reap
    -0.11
     '../../../../../
    -0.11
    olt
    -0.11
    ",{
    -0.11
    -Regular
    -0.10
    ment
    -0.10
    문
    -0.10
    uations
    -0.10
    POSITIVE LOGITS
    overs
    0.10
    ëł¥
    0.09
    /compiler
    0.08
    /memory
    0.08
    noon
    0.08
     :</
    0.07
     tic
    0.07
     predominant
    0.07
    /em
    0.07
     quotient
    0.07
    Activations Density 0.044%

    No Known Activations