© 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. 115745
    Prev
    Next
    INDEX
    Explanations

    pixel display or lenses

    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
     Pend
    -0.11
     pend
    -0.11
    legate
    -0.09
    langs
    -0.09
    inez
    -0.09
     Nim
    -0.09
    heck
    -0.08
     swinger
    -0.08
     pendant
    -0.08
    reo
    -0.08
    POSITIVE LOGITS
    ated
    0.13
    shader
    0.10
     perfect
    0.10
    /frame
    0.09
    _shader
    0.09
    eer
    0.09
    ilated
    0.09
    shuffle
    0.09
    Pix
    0.09
    atively
    0.09
    Activations Density 0.046%

    No Known Activations