© 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. 33361
    Prev
    Next
    INDEX
    Explanations

    standalone electronic, standalone interpreter, standalone web, standalone editor, standalone VR, standalone computers

    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
    ster
    -0.13
    ry
    -0.12
    iga
    -0.12
    Ter
    -0.11
    heets
    -0.11
     Pry
    -0.10
    -Le
    -0.10
    tram
    -0.10
     Humb
    -0.10
     Kramer
    -0.10
    POSITIVE LOGITS
    /is
    0.08
     ort
    0.08
     forgetting
    0.08
     casual
    0.08
     single
    0.08
    bserv
    0.08
     piece
    0.08
    -ish
    0.08
    anness
    0.07
     completeness
    0.07
    Activations Density 0.006%

    No Known Activations