© 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. 7717
    Prev
    Next
    INDEX
    Explanations

    imp followed by words like air, otent, asse, ressive, et

    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
     Hammond
    -0.08
    imal
    -0.08
    件
    -0.08
     outdoors
    -0.08
     ec
    -0.08
    efs
    -0.08
    elier
    -0.08
    ingly
    -0.08
    orrow
    -0.08
    igu
    -0.08
    POSITIVE LOGITS
     imp
    0.20
     Imp
    0.19
    imp
    0.18
    Imp
    0.17
     impuls
    0.16
    regn
    0.16
     IMP
    0.15
    rompt
    0.14
     impart
    0.14
     impulse
    0.14
    Activations Density 0.030%

    No Known Activations