© 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. 88005
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or identifiers

    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
    eh
    -0.10
    hips
    -0.10
    ees
    -0.10
    uos
    -0.10
    eu
    -0.09
    ee
    -0.09
    ea
    -0.09
    ehr
    -0.09
    ह
    -0.09
    ØŃ
    -0.09
    POSITIVE LOGITS
    ERSHEY
    0.16
    edral
    0.15
    aupt
    0.14
    è¾ij
    0.13
    hh
    0.13
    hhh
    0.13
    awk
    0.12
    ysics
    0.12
    olland
    0.12
    undred
    0.12
    Activations Density 0.854%

    No Known Activations