© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114250
    Prev
    Next
    INDEX
    Explanations

    fine powders, KeyFit, PCR, trace, http, enclosure

    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
     geographical
    -0.08
    ifestyles
    -0.08
     domicile
    -0.08
    owntown
    -0.07
    (getApplicationContext
    -0.07
     spatial
    -0.07
     rural
    -0.07
    ://{
    -0.07
    unicip
    -0.07
     outdoors
    -0.07
    POSITIVE LOGITS
     ($.
    0.09
     compilers
    0.09
     Nobel
    0.09
     pestic
    0.09
     compiler
    0.09
     lorem
    0.08
    _serializer
    0.08
     formul
    0.08
     ffmpeg
    0.08
     Pulitzer
    0.08
    Activations Density 5.876%

    No Known Activations